WeNet CTC-based models

This page lists all offline CTC models from WeNet.

sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03 (吴语)

This model is converted from

https://huggingface.co/ASLP-lab/WenetSpeech-Wu-Speech-Understanding/tree/main/u2++

It uses 8k hours of training data.

It supports Shanghainese, Suzhounese, Shaoxingnese, Ningbonese, Hangzhounese, Jiaxingnese, Taizhounese, and Wenzhounese.

Hint

该模型支持

普通话

上海话

苏州话

绍兴话

宁波话

杭州话

嘉兴话

台州话

温州话

Huggingface space

You can visit

https://huggingface.co/spaces/k2-fsa/automatic-speech-recognition

to try this model in your browser.

Hint

You need to first select the language 吴语 and then select the model csukuangfj2/sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03.

Android APKs

Real-time speech recognition Android APKs can be found at

https://k2-fsa.github.io/sherpa/onnx/android/apk-simulate-streaming-asr.html

Hint

Please always download the latest version.

Please search for wu-wenetspeech_wu_u2pconformer_ctc_2026_02_03.

Download

Please use the following commands to download it:

cd /path/to/sherpa-onnx

wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03.tar.bz2
tar xf sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03.tar.bz2
rm sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03.tar.bz2

After downloading, you should find the following files:

ls -lh sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/
total 264120
-rw-r--r--@  1 fangjun  staff   127M  3 Feb 18:44 model.int8.onnx
-rw-r--r--@  1 fangjun  staff   239B  3 Feb 18:44 README.md
drwxr-xr-x@ 27 fangjun  staff   864B  3 Feb 18:44 test_wavs
-rw-r--r--@  1 fangjun  staff    51K  3 Feb 18:44 tokens.txt

ls -lh sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/
total 10888
-rw-r--r--@ 1 fangjun  staff   184K  3 Feb 18:44 1.wav
-rw-r--r--@ 1 fangjun  staff   238K  3 Feb 18:44 10.wav
-rw-r--r--@ 1 fangjun  staff   228K  3 Feb 18:44 11.wav
-rw-r--r--@ 1 fangjun  staff   179K  3 Feb 18:44 12.wav
-rw-r--r--@ 1 fangjun  staff   214K  3 Feb 18:44 13.wav
-rw-r--r--@ 1 fangjun  staff   374K  3 Feb 18:44 14.wav
-rw-r--r--@ 1 fangjun  staff   383K  3 Feb 18:44 15.wav
-rw-r--r--@ 1 fangjun  staff   181K  3 Feb 18:44 16.wav
-rw-r--r--@ 1 fangjun  staff   181K  3 Feb 18:44 17.wav
-rw-r--r--@ 1 fangjun  staff   186K  3 Feb 18:44 18.wav
-rw-r--r--@ 1 fangjun  staff   181K  3 Feb 18:44 19.wav
-rw-r--r--@ 1 fangjun  staff   183K  3 Feb 18:44 2.wav
-rw-r--r--@ 1 fangjun  staff   238K  3 Feb 18:44 20.wav
-rw-r--r--@ 1 fangjun  staff   193K  3 Feb 18:44 21.wav
-rw-r--r--@ 1 fangjun  staff   184K  3 Feb 18:44 22.wav
-rw-r--r--@ 1 fangjun  staff   264K  3 Feb 18:44 23.wav
-rw-r--r--@ 1 fangjun  staff   180K  3 Feb 18:44 24.wav
-rw-r--r--@ 1 fangjun  staff   251K  3 Feb 18:44 3.wav
-rw-r--r--@ 1 fangjun  staff   229K  3 Feb 18:44 4.wav
-rw-r--r--@ 1 fangjun  staff   257K  3 Feb 18:44 5.wav
-rw-r--r--@ 1 fangjun  staff   218K  3 Feb 18:44 6.wav
-rw-r--r--@ 1 fangjun  staff   241K  3 Feb 18:44 7.wav
-rw-r--r--@ 1 fangjun  staff   183K  3 Feb 18:44 8.wav
-rw-r--r--@ 1 fangjun  staff   234K  3 Feb 18:44 9.wav
-rw-r--r--@ 1 fangjun  staff   2.0K  3 Feb 18:44 transcript.txt

Real-time/Streaming Speech recognition from a microphone with VAD

wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx

./build/bin/sherpa-onnx-vad-microphone-simulated-streaming-asr \
  --silero-vad-model=./silero_vad.onnx \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1

Decode wave files

1.wav

Wave filename	Content	Ground truth
1.wav		而宋子文搭子宋美龄搭子端纳呢侪没经过搜查

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/1.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/1.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.179 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/1.wav
{"lang": "", "emotion": "", "event": "", "text": "而宋子文搭子宋美龄搭子端纳呢侪没经过搜查", "timestamps": [0.76, 1.00, 1.24, 1.44, 1.60, 1.72, 1.92, 2.16, 2.36, 2.52, 2.68, 2.92, 3.16, 3.36, 3.92, 4.24, 4.44, 4.64, 4.88, 5.12], "durations": [], "tokens":["而", "宋", "子", "文", "搭", "子", "宋", "美", "龄", "搭", "子", "端", "纳", "呢", "侪", "没", "经", "过", "搜", "查"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.232 s
Real time factor (RTF): 0.232 / 5.880 = 0.039

2.wav

Wave filename	Content	Ground truth
2.wav		借搿个机会纷纷响应搿个辰光奥地利个老皇帝已经死脱了

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/2.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/2.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.166 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/2.wav
{"lang": "", "emotion": "", "event": "", "text": "借搿个机会纷纷响应搿个辰光奥地利的老皇帝已经死脱了", "timestamps": [0.52, 0.72, 0.84, 0.96, 1.12, 1.32, 1.52, 1.72, 1.92, 3.00, 3.16, 3.24, 3.36, 3.52, 3.68, 3.84, 3.96, 4.12, 4.28, 4.44, 4.56, 4.64, 4.80, 4.96, 5.12], "durations": [], "tokens":["借", "搿", "个", "机", "会", "纷", "纷", "响", "应", "搿", "个", "辰", "光", "奥", "地", "利", "的", "老", "皇", "帝", "已", "经", "死", "脱", "了"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.234 s
Real time factor (RTF): 0.234 / 5.860 = 0.040

3.wav

Wave filename	Content	Ground truth
3.wav		呃大灰狼就跟山羊奶奶讲山羊奶奶侬一家头蹲阿拉决定拿这点物事侪送拨侬

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/3.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/3.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.187 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/3.wav
{"lang": "", "emotion": "", "event": "", "text": "呃大灰狼就跟山羊奶奶讲山羊奶奶侬一家头等阿拉酒弟拿这点物事侪送拨侬", "timestamps": [0.96, 1.68, 1.80, 1.96, 2.08, 2.24, 2.36, 2.52, 2.68, 2.80, 2.92, 3.08, 3.20, 3.36, 3.52, 4.04, 4.20, 4.36, 4.52, 4.76, 5.40, 5.52, 5.68, 5.80, 5.96, 6.08, 6.20, 6.36, 6.48, 6.56, 6.72, 6.88, 7.04], "durations": [], "tokens":["呃", "大", "灰", "狼", "就", "跟", "山", "羊", "奶", "奶", "讲", "山", "羊", "奶", "奶", "侬", "一", "家", "头", "等", "阿", "拉", "酒", "弟", "拿", "这", "点", "物", "事", "侪", "送", "拨", "侬"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.320 s
Real time factor (RTF): 0.320 / 8.040 = 0.040

4.wav

Wave filename	Content	Ground truth
4.wav		胖胖又得意了啥人会得想到玩具汽车里头还囥了物事呢

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/4.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/4.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.171 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/4.wav
{"lang": "", "emotion": "", "event": "", "text": "胖胖又得意了呵啥人会得想到玩具汽车里头还囥了物事呢", "timestamps": [1.64, 1.76, 1.92, 2.16, 2.32, 2.48, 2.84, 3.28, 3.44, 3.56, 3.68, 3.84, 4.04, 4.72, 4.96, 5.20, 5.44, 5.60, 5.76, 5.84, 6.00, 6.20, 6.32, 6.44, 6.60], "durations": [], "tokens":["胖", "胖", "又", "得", "意", "了", "呵", "啥", "人", "会", "得", "想", "到", "玩", "具", "汽", "车", "里", "头", "还", "囥", "了", "物", "事", "呢"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.294 s
Real time factor (RTF): 0.294 / 7.340 = 0.040

5.wav

Wave filename	Content	Ground truth
5.wav		这物事里头是有利益分配的讲好个埃种大生意难做一趟做两三年也做不出的

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/5.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/5.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.171 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/5.wav
{"lang": "", "emotion": "", "event": "", "text": "这物是里都是有利益分配的讲好的埃种大生意难做一趟做两三年也做不出的", "timestamps": [0.48, 0.60, 0.76, 0.88, 1.04, 1.20, 1.48, 1.72, 1.92, 2.08, 2.28, 2.48, 2.64, 2.88, 3.08, 3.84, 4.04, 4.20, 4.40, 4.60, 4.84, 5.08, 5.28, 5.40, 6.28, 6.48, 6.72, 6.88, 7.00, 7.16, 7.28, 7.40, 7.56], "durations": [], "tokens":["这", "物", "是", "里", "都", "是", "有", "利", "益", "分", "配", "的", "讲", "好", "的", "埃", "种", "大", "生", "意", "难", "做", "一", "趟", "做", "两", "三", "年", "也", "做", "不", "出", "的"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.329 s
Real time factor (RTF): 0.329 / 8.220 = 0.040

6.wav

Wave filename	Content	Ground truth
6.wav		这个新生儿啊相对来讲偏少大家侪不愿意生嘛

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/6.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/6.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.168 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/6.wav
{"lang": "", "emotion": "", "event": "", "text": "这个新生儿啊相对来讲偏少大家侪不愿意伤嘛", "timestamps": [0.48, 0.68, 1.84, 2.04, 2.28, 2.52, 3.08, 3.28, 3.40, 3.56, 3.76, 3.96, 4.68, 4.84, 4.96, 5.08, 5.20, 5.32, 5.48, 5.72], "durations": [], "tokens":["这", "个", "新", "生", "儿", "啊", "相", "对", "来", "讲", "偏", "少", "大", "家", "侪", "不", "愿", "意", "伤", "嘛"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.279 s
Real time factor (RTF): 0.279 / 6.960 = 0.040

7.wav

Wave filename	Content	Ground truth
7.wav		这自然应该是像上海大都市这能介告诉伊虽然伊同样是外来的闲话

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/7.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/7.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.184 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/7.wav
{"lang": "", "emotion": "", "event": "", "text": "这自然应该是像上海大都市这样个告所以虽然同样是外来个闲话", "timestamps": [0.48, 0.68, 0.84, 1.24, 1.40, 1.52, 1.68, 1.88, 2.08, 2.32, 2.56, 2.72, 2.88, 3.04, 3.16, 4.24, 4.44, 4.64, 5.36, 5.56, 5.80, 5.96, 6.12, 6.36, 6.52, 6.68, 6.80, 6.96], "durations": [], "tokens":["这", "自", "然", "应", "该", "是", "像", "上", "海", "大", "都", "市", "这", "样", "个", "告", "所", "以", "虽", "然", "同", "样", "是", "外", "来", "个", "闲", "话"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.311 s
Real time factor (RTF): 0.311 / 7.720 = 0.040

8.wav

Wave filename	Content	Ground truth
8.wav		已经有西南亚洲的外国人居住辣辣埃及从事贸易活动

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/8.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/8.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.177 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/8.wav
{"lang": "", "emotion": "", "event": "", "text": "已经由西南亚洲的外国人居住辣辣埃及从事贸易活动", "timestamps": [0.48, 0.64, 0.80, 1.08, 1.32, 1.60, 1.92, 2.08, 2.28, 2.48, 2.64, 2.88, 3.12, 3.32, 3.44, 3.64, 3.84, 4.04, 4.28, 4.64, 4.88, 5.00, 5.12], "durations": [], "tokens":["已", "经", "由", "西", "南", "亚", "洲", "的", "外", "国", "人", "居", "住", "辣", "辣", "埃", "及", "从", "事", "贸", "易", "活", "动"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.233 s
Real time factor (RTF): 0.233 / 5.860 = 0.040

9.wav

Wave filename	Content	Ground truth
9.wav		青春的舞龙唱出短暂的曲子的清风里后世

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/9.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/9.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.171 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/9.wav
{"lang": "", "emotion": "", "event": "", "text": "清脆的舞咙唱出婉转的曲子搭清风的流", "timestamps": [0.56, 0.88, 1.16, 1.32, 1.56, 2.48, 2.76, 3.24, 3.56, 3.84, 4.16, 4.36, 5.36, 5.84, 6.20, 6.40, 6.56], "durations": [], "tokens":["清", "脆", "的", "舞", "咙", "唱", "出", "婉", "转", "的", "曲", "子", "搭", "清", "风", "的", "流"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.298 s
Real time factor (RTF): 0.298 / 7.480 = 0.040

10.wav

Wave filename	Content	Ground truth
10.wav		肠道菌群也就是阿拉肠道当中不同种类的细菌等微生物会的影响大脑的健康

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/10.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/10.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.166 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/10.wav
{"lang": "", "emotion": "", "event": "", "text": "肠道菌群也就是阿拉肠道当中不同种类的细菌等微生物会得影响大脑的健康", "timestamps": [0.64, 0.88, 1.12, 1.32, 2.44, 2.60, 2.72, 2.80, 2.88, 3.04, 3.20, 3.32, 3.48, 3.60, 3.72, 3.92, 4.08, 4.24, 4.36, 4.56, 4.76, 5.00, 5.20, 5.36, 5.52, 5.64, 5.76, 5.96, 6.16, 6.32, 6.48, 6.60, 6.80], "durations": [], "tokens":["肠", "道", "菌", "群", "也", "就", "是", "阿", "拉", "肠", "道", "当", "中", "不", "同", "种", "类", "的", "细", "菌", "等", "微", "生", "物", "会", "得", "影", "响", "大", "脑", "的", "健", "康"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.302 s
Real time factor (RTF): 0.302 / 7.600 = 0.040

11.wav

Wave filename	Content	Ground truth
11.wav		老百姓大家知了伊也勿中浪向摊头浪向吃两碗豆腐花

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/11.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/11.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.166 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/11.wav
{"lang": "", "emotion": "", "event": "", "text": "老百姓大家醉了伊也勿中浪向摊头浪向吃两碗豆腐花", "timestamps": [0.60, 0.88, 1.04, 1.28, 1.48, 1.72, 1.92, 2.08, 2.20, 2.40, 3.64, 3.96, 4.20, 4.60, 4.84, 5.00, 5.24, 5.52, 5.68, 5.88, 6.12, 6.28, 6.44], "durations": [], "tokens":["老", "百", "姓", "大", "家", "醉", "了", "伊", "也", "勿", "中", "浪", "向", "摊", "头", "浪", "向", "吃", "两", "碗", "豆", "腐", "花"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.292 s
Real time factor (RTF): 0.292 / 7.300 = 0.040

12.wav

Wave filename	Content	Ground truth
12.wav		孙女告娘当我儿子看我讲的闲话

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/12.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/12.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.172 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/12.wav
{"lang": "", "emotion": "", "event": "", "text": "孙权的娘当我儿子的我讲的闲话", "timestamps": [0.60, 1.08, 1.24, 1.44, 1.80, 1.96, 2.20, 2.52, 2.80, 3.88, 4.24, 4.44, 4.60, 4.80], "durations": [], "tokens":["孙", "权", "的", "娘", "当", "我", "儿", "子", "的", "我", "讲", "的", "闲", "话"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.226 s
Real time factor (RTF): 0.226 / 5.740 = 0.039

13.wav

Wave filename	Content	Ground truth
13.wav		呃对伐现在实际上是新上海人越来越多了外加未来我觉着这群新上海人会得取代脱阿拉

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/13.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/13.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.164 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/13.wav
{"lang": "", "emotion": "", "event": "", "text": "啊对伐现在实际上是新上海人越来越多了外加未来我觉着这句新上海人会的取略脱阿拉", "timestamps": [0.52, 0.88, 1.04, 1.24, 1.32, 1.44, 1.56, 1.64, 1.76, 2.12, 2.28, 2.44, 2.52, 2.64, 2.72, 2.84, 2.92, 3.04, 3.40, 3.52, 3.76, 3.88, 4.04, 4.12, 4.24, 4.72, 4.84, 4.96, 5.08, 5.20, 5.32, 5.40, 5.48, 5.60, 5.72, 5.84, 5.96, 6.04], "durations": [], "tokens":["啊", "对", "伐", "现", "在", "实", "际", "上", "是", "新", "上", "海", "人", "越", "来", "越", "多", "了", "外", "加", "未", "来", "我", "觉", "着", "这", "句", "新", "上", "海", "人", "会", "的", "取", "略", "脱", "阿", "拉"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.272 s
Real time factor (RTF): 0.272 / 6.840 = 0.040

14.wav

Wave filename	Content	Ground truth
14.wav		有搿种爷娘对伐但是我觉着现在好像就讲上海哦现在勿是侪讲房子也没人住嘛外国人跑得一批还有就是叫低生育率帮低结婚率嗯

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/14.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/14.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.179 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/14.wav
{"lang": "", "emotion": "", "event": "", "text": "呃有搿种爷娘对伐但是我觉着现在好像就讲上海哦现在勿是侪讲房子也没人住嘛外国人跑得一批还有就是叫低生育率帮低结婚率嗯", "timestamps": [0.48, 0.72, 0.84, 1.04, 1.16, 1.36, 1.68, 1.80, 2.04, 2.16, 2.28, 2.40, 2.52, 2.68, 2.84, 3.00, 3.16, 3.48, 3.60, 3.80, 3.96, 4.08, 4.28, 4.40, 4.60, 4.72, 4.88, 5.04, 5.24, 5.40, 5.68, 5.84, 5.96, 6.12, 6.32, 6.60, 6.76, 6.88, 7.00, 7.16, 7.24, 7.36, 7.48, 7.60, 7.68, 7.80, 7.88, 8.20, 8.56, 8.80, 9.00, 9.36, 9.68, 9.92, 10.08, 10.24, 10.52], "durations": [], "tokens":["呃", "有", "搿", "种", "爷", "娘", "对", "伐", "但", "是", "我", "觉", "着", "现", "在", "好", "像", "就", "讲", "上", "海", "哦", "现", "在", "勿", "是", "侪", "讲", "房", "子", "也", "没", "人", "住", "嘛", "外", "国", "人", "跑", "得", "一", "批", "还", "有", "就", "是", "叫", "低", "生", "育", "率", "帮", "低", "结", "婚", "率", "嗯"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.489 s
Real time factor (RTF): 0.489 / 11.960 = 0.041

15.wav

Wave filename	Content	Ground truth
15.wav		当侬老了一个人头发花白坐辣盖落花旁边轻轻的从书架上面取下一本书来慢慢叫的阅读

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/15.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/15.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.172 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/15.wav
{"lang": "", "emotion": "", "event": "", "text": "当侬老了一个人头发花白坐辣盖芦花旁边轻轻的从书界上面取下一本书来慢慢叫的阅读", "timestamps": [0.48, 0.72, 1.04, 1.36, 2.92, 3.08, 3.24, 3.68, 3.88, 4.08, 4.32, 5.20, 5.40, 5.52, 5.72, 5.92, 6.16, 6.40, 7.08, 7.32, 7.52, 7.84, 8.04, 8.24, 8.44, 8.68, 8.96, 9.16, 9.32, 9.48, 9.68, 9.96, 10.44, 10.68, 10.84, 11.00, 11.16, 11.32], "durations": [], "tokens":["当", "侬", "老", "了", "一", "个", "人", "头", "发", "花", "白", "坐", "辣", "盖", "芦", "花", "旁", "边", "轻", "轻", "的", "从", "书", "界", "上", "面", "取", "下", "一", "本", "书", "来", "慢", "慢", "叫", "的", "阅", "读"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.505 s
Real time factor (RTF): 0.505 / 12.240 = 0.041

16.wav

Wave filename	Content	Ground truth
16.wav		伴着夕阳的余晖一切侪是最美好的样子

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/16.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/16.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.178 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/16.wav
{"lang": "", "emotion": "", "event": "", "text": "伴着夕洋个余晖一切侪是最美好个样子", "timestamps": [0.48, 0.72, 1.00, 1.20, 1.40, 1.60, 1.84, 2.60, 2.80, 3.16, 3.36, 3.56, 3.80, 4.08, 4.32, 4.48, 4.80], "durations": [], "tokens":["伴", "着", "夕", "洋", "个", "余", "晖", "一", "切", "侪", "是", "最", "美", "好", "个", "样", "子"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.239 s
Real time factor (RTF): 0.239 / 5.780 = 0.041

17.wav

Wave filename	Content	Ground truth
17.wav		勿晓得个呀老早勿是讲旧社会个辰光嘛搿种流氓阿了

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/17.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/17.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.176 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/17.wav
{"lang": "", "emotion": "", "event": "", "text": "勿晓得个呀老早勿是讲旧社会个辰光嘛搿种流氓也费了", "timestamps": [0.52, 0.68, 0.80, 0.96, 1.04, 2.24, 2.40, 2.48, 2.56, 2.64, 2.76, 2.92, 3.08, 3.20, 3.32, 3.44, 3.64, 3.76, 3.84, 4.56, 4.76, 4.84, 4.96, 5.12], "durations": [], "tokens":["勿", "晓", "得", "个", "呀", "老", "早", "勿", "是", "讲", "旧", "社", "会", "个", "辰", "光", "嘛", "搿", "种", "流", "氓", "也", "费", "了"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.232 s
Real time factor (RTF): 0.232 / 5.780 = 0.040

18.wav

Wave filename	Content	Ground truth
18.wav		观众朋友们就是教个小诀窍就是屋里向大家一直拌馄饨芯子啊

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/18.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/18.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.183 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/18.wav
{"lang": "", "emotion": "", "event": "", "text": "观众朋友们就是教搞小诀窍就是屋里向大家一直拌馄饨芯子啊", "timestamps": [0.44, 0.60, 0.76, 0.92, 1.04, 1.20, 1.32, 1.80, 2.00, 2.16, 2.32, 2.48, 2.88, 3.04, 3.32, 3.44, 3.56, 3.80, 3.96, 4.08, 4.16, 4.36, 4.56, 4.72, 4.88, 5.04, 5.20], "durations": [], "tokens":["观", "众", "朋", "友", "们", "就", "是", "教", "搞", "小", "诀", "窍", "就", "是", "屋", "里", "向", "大", "家", "一", "直", "拌", "馄", "饨", "芯", "子", "啊"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.243 s
Real time factor (RTF): 0.243 / 5.940 = 0.041

19.wav

Wave filename	Content	Ground truth
19.wav		哦对的对的侬讲了对的哎哟这小米侬还是侬脑子好

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/19.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/19.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.182 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/19.wav
{"lang": "", "emotion": "", "event": "", "text": "哦对的对的侬讲了对的哎哟迭小米侬还是侬脑子好", "timestamps": [0.48, 1.12, 1.32, 2.08, 2.20, 2.32, 2.44, 2.56, 2.64, 2.80, 3.16, 3.32, 3.64, 3.76, 3.92, 4.04, 4.24, 4.36, 4.52, 4.68, 4.84, 5.00], "durations": [], "tokens":["哦", "对", "的", "对", "的", "侬", "讲", "了", "对", "的", "哎", "哟", "迭", "小", "米", "侬", "还", "是", "侬", "脑", "子", "好"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.233 s
Real time factor (RTF): 0.233 / 5.780 = 0.040

20.wav

Wave filename	Content	Ground truth
20.wav		嗯沿海各地包括㑚南翔连是日本海的前头一个费城

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/20.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/20.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.176 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/20.wav
{"lang": "", "emotion": "", "event": "", "text": "嗯沿海各地包括南南洋嗯伊是日本海达集头一个返城", "timestamps": [0.48, 1.64, 1.88, 2.08, 2.24, 2.56, 2.72, 2.88, 3.16, 3.36, 3.72, 4.20, 4.36, 4.56, 4.76, 5.04, 5.32, 5.72, 5.88, 6.16, 6.28, 6.48, 6.76], "durations": [], "tokens":["嗯", "沿", "海", "各", "地", "包", "括", "南", "南", "洋", "嗯", "伊", "是", "日", "本", "海", "达", "集", "头", "一", "个", "返", "城"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.311 s
Real time factor (RTF): 0.311 / 7.600 = 0.041

21.wav

Wave filename	Content	Ground truth
21.wav		侬就没命了为了不叫类似的事体再发生张晨

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/21.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/21.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.174 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/21.wav
{"lang": "", "emotion": "", "event": "", "text": "侬就没命了为了不让类似的事体再发生张晨", "timestamps": [0.60, 0.76, 0.96, 1.16, 1.32, 2.24, 2.40, 2.52, 2.68, 2.96, 3.24, 3.40, 3.52, 3.60, 3.76, 3.92, 4.04, 4.96, 5.24], "durations": [], "tokens":["侬", "就", "没", "命", "了", "为", "了", "不", "让", "类", "似", "的", "事", "体", "再", "发", "生", "张", "晨"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.252 s
Real time factor (RTF): 0.252 / 6.160 = 0.041

22.wav

Wave filename	Content	Ground truth
22.wav		其实这两年我也就是行尸走肉因为老婆没了

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/22.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/22.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.177 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/22.wav
{"lang": "", "emotion": "", "event": "", "text": "其实这两年我也就是行势走肉因为老婆没了", "timestamps": [0.56, 0.72, 0.84, 1.00, 1.16, 1.32, 1.48, 1.60, 1.76, 2.16, 2.44, 2.72, 2.92, 4.32, 4.44, 4.64, 4.80, 4.96, 5.08], "durations": [], "tokens":["其", "实", "这", "两", "年", "我", "也", "就", "是", "行", "势", "走", "肉", "因", "为", "老", "婆", "没", "了"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.240 s
Real time factor (RTF): 0.240 / 5.900 = 0.041

23.wav

Wave filename	Content	Ground truth
23.wav		对的呀末伊拉这评论里向有种侬要讲一个人真个红了对勿啦就讲侬粉丝超过一万了嘛侬这种黑粉丝多

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/23.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/23.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.171 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/23.wav
{"lang": "", "emotion": "", "event": "", "text": "对的呀对么伊拉搿评论里向有种侬要讲一个人真个红了对伐啦就讲侬粉丝超过一万了嘛侬搿种黑粉是多", "timestamps": [0.48, 0.60, 0.68, 0.80, 0.88, 1.28, 1.36, 1.48, 1.68, 1.84, 2.00, 2.12, 2.32, 2.48, 2.84, 3.00, 3.16, 3.56, 3.68, 3.80, 4.40, 4.56, 4.72, 4.92, 5.00, 5.12, 5.20, 5.36, 5.52, 5.68, 5.80, 5.96, 6.12, 6.24, 6.36, 6.48, 6.60, 6.72, 6.92, 7.00, 7.12, 7.24, 7.40, 7.56, 7.76], "durations": [], "tokens":["对", "的", "呀", "对", "么", "伊", "拉", "搿", "评", "论", "里", "向", "有", "种", "侬", "要", "讲", "一", "个", "人", "真", "个", "红", "了", "对", "伐", "啦", "就", "讲", "侬", "粉", "丝", "超", "过", "一", "万", "了", "嘛", "侬", "搿", "种", "黑", "粉", "是", "多"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.346 s
Real time factor (RTF): 0.346 / 8.460 = 0.041

24.wav

Wave filename	Content	Ground truth
24.wav		正常保养电池呃电瓶啊搿种轮胎啊还有

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/24.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:373 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx --num-threads=1 ./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/24.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), omnilingual=OfflineOmnilingualAsrCtcModelConfig(model=""), funasr_nano=OfflineFunASRNanoModelConfig(encoder_adaptor="", llm="", embedding="", tokenizer="", system_prompt="You are a helpful assistant.", user_prompt="语音转写：", max_new_tokens=512, temperature=1e-06, top_p=0.8, seed=42), medasr=OfflineMedAsrCtcModelConfig(model=""), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(lexicon="", rule_fsts=""))
Creating recognizer ...
recognizer created in 0.184 s
Started
Done!

./sherpa-onnx-wenetspeech-wu-u2pp-conformer-ctc-zh-int8-2026-02-03/test_wavs/24.wav
{"lang": "", "emotion": "", "event": "", "text": "正常保养电视呃电瓶啊搿种轮胎啊还有", "timestamps": [0.48, 0.64, 0.76, 0.96, 1.28, 1.44, 1.64, 1.92, 2.04, 2.20, 2.80, 3.00, 3.20, 3.36, 3.56, 4.44, 4.60], "durations": [], "tokens":["正", "常", "保", "养", "电", "视", "呃", "电", "瓶", "啊", "搿", "种", "轮", "胎", "啊", "还", "有"], "ys_log_probs": [], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.233 s
Real time factor (RTF): 0.233 / 5.760 = 0.040

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10 (Cantonese, 粤语)

This model is converted from

https://huggingface.co/ASLP-lab/WSYue-ASR/tree/main/u2pp_conformer_yue

It uses 21.8k hours of training data.

Hint

If you want a Cantonese ASR model, please choose this model or sherpa-onnx-sense-voice-zh-en-ja-ko-yue-int8-2025-09-09 (Chinese, English, Japanese, Korean, Cantonese, 中英日韩粤语)

Huggingface space

You can visit

https://huggingface.co/spaces/k2-fsa/automatic-speech-recognition

to try this model in your browser.

Hint

You need to first select the language Cantonese and then select the model csukuangfj/sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10.

Android APKs

Real-time speech recognition Android APKs can be found at

https://k2-fsa.github.io/sherpa/onnx/android/apk-simulate-streaming-asr.html

Hint

Please always download the latest version.

Please search for wenetspeech_yue_u2pconformer_ctc_2025_09_10.

Download

Please use the following commands to download it:

cd /path/to/sherpa-onnx

wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10.tar.bz2
tar xf sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10.tar.bz2
rm sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10.tar.bz2

After downloading, you should find the following files:

ls -lh sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/

total 263264
-rw-r--r--   1 fangjun  staff   129B Sep 10 14:18 README.md
-rw-r--r--   1 fangjun  staff   128M Sep 10 14:18 model.int8.onnx
drwxr-xr-x  22 fangjun  staff   704B Sep 10 14:18 test_wavs
-rw-r--r--   1 fangjun  staff    83K Sep 10 14:18 tokens.txt

Real-time/Streaming Speech recognition from a microphone with VAD

wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx

./build/bin/sherpa-onnx-vad-microphone-simulated-streaming-asr \
  --silero-vad-model=./silero_vad.onnx \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1

Decode wave files

yue-0.wav

Wave filename	Content	Ground truth
yue-0.wav		两只小企鹅都有嘢食

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-0.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-0.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-0.wav
{"lang": "", "emotion": "", "event": "", "text": "两只小企鹅都有嘢食", "timestamps": [0.48, 0.68, 0.92, 1.16, 1.36, 1.84, 2.00, 2.20, 2.40], "tokens":["两", "只", "小", "企", "鹅", "都", "有", "嘢", "食"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.226 s
Real time factor (RTF): 0.226 / 3.072 = 0.074

yue-1.wav

Wave filename	Content	Ground truth
yue-1.wav		叫做诶诶直入式你个脑部里边咧记得呢一个嘅以前香港有一个广告好出名嘅佢乜嘢都冇噶净系影住喺弥敦道佢哋间铺头嘅啫但系就不停有人嗌啦平平吧平吧

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-1.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-1.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-1.wav
{"lang": "", "emotion": "", "event": "", "text": "叫做诶诶直入式你个脑部里边咧记得呢一个嘅以前香港有一个广告好出名嘅佢乜嘢都冇噶净系影住喺弥敦道佢哋间铺头嘅啫但系就不停有人嗌啦平平吧平吧", "timestamps": [0.04, 0.16, 0.36, 0.84, 1.16, 1.40, 1.64, 1.88, 2.00, 2.24, 2.56, 2.76, 2.92, 3.08, 3.28, 3.44, 3.60, 3.68, 3.80, 4.00, 4.20, 4.36, 4.52, 4.64, 4.76, 4.84, 4.92, 5.04, 5.16, 5.32, 5.48, 5.64, 5.88, 6.48, 6.64, 6.80, 6.92, 7.08, 7.24, 7.60, 7.72, 7.88, 8.04, 8.16, 8.36, 8.52, 8.72, 8.88, 9.00, 9.20, 9.36, 9.48, 9.64, 9.80, 10.12, 10.20, 10.32, 10.52, 10.64, 10.80, 10.88, 11.04, 11.24, 12.04, 12.84, 13.08, 13.96, 14.20], "tokens":["叫", "做", "诶", "诶", "直", "入", "式", "你", "个", "脑", "部", "里", "边", "咧", "记", "得", "呢", "一", "个", "嘅", "以", "前", "香", "港", "有", "一", "个", "广", "告", "好", "出", "名", "嘅", "佢", "乜", "嘢", "都", "冇", "噶", "净", "系", "影", "住", "喺", "弥", "敦", "道", "佢", "哋", "间", "铺", "头", "嘅", "啫", "但", "系", "就", "不", "停", "有", "人", "嗌", "啦", "平", "平", "吧", "平", "吧"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.185 s
Real time factor (RTF): 1.185 / 15.104 = 0.078

yue-2.wav

Wave filename	Content	Ground truth
yue-2.wav		忽然从光线死角嘅阴影度窜出一只大猫

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-2.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-2.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-2.wav
{"lang": "", "emotion": "", "event": "", "text": "忽然从光线死角嘅阴影度传出一只大猫", "timestamps": [0.44, 0.56, 1.16, 1.36, 1.64, 1.92, 2.12, 2.24, 2.36, 2.56, 2.80, 3.16, 3.36, 3.52, 3.64, 3.80, 3.96], "tokens":["忽", "然", "从", "光", "线", "死", "角", "嘅", "阴", "影", "度", "传", "出", "一", "只", "大", "猫"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.369 s
Real time factor (RTF): 0.369 / 4.608 = 0.080

yue-3.wav

Wave filename	Content	Ground truth
yue-3.wav		今日我带大家去见识一位九零后嘅靓仔咧

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-3.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-3.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-3.wav
{"lang": "", "emotion": "", "event": "", "text": "今日我带大家去见识一位九零后嘅靓仔咧", "timestamps": [0.32, 0.48, 0.60, 0.72, 0.92, 1.08, 1.56, 1.76, 1.96, 2.12, 2.24, 2.56, 2.80, 3.04, 3.20, 3.36, 3.56, 3.80], "tokens":["今", "日", "我", "带", "大", "家", "去", "见", "识", "一", "位", "九", "零", "后", "嘅", "靓", "仔", "咧"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.380 s
Real time factor (RTF): 0.380 / 4.352 = 0.087

yue-4.wav

Wave filename	Content	Ground truth
yue-4.wav		香港嘅消费市场从此不一样

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-4.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-4.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-4.wav
{"lang": "", "emotion": "", "event": "", "text": "香港嘅消费市场从此不一样", "timestamps": [0.44, 0.64, 0.80, 0.96, 1.16, 1.44, 1.64, 1.96, 2.16, 2.44, 2.64, 2.80], "tokens":["香", "港", "嘅", "消", "费", "市", "场", "从", "此", "不", "一", "样"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.228 s
Real time factor (RTF): 0.228 / 3.200 = 0.071

yue-5.wav

Wave filename	Content	Ground truth
yue-5.wav		景天谂唔到呢个守门嘅弟子竟然咁无礼霎时间面色都变埋

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-5.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-5.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-5.wav
{"lang": "", "emotion": "", "event": "", "text": "景天谂唔到呢个守门嘅弟子竟然咁无礼霎时间面色都变埋", "timestamps": [0.52, 0.72, 1.00, 1.12, 1.24, 1.40, 1.52, 1.68, 1.92, 2.08, 2.20, 2.40, 3.12, 3.28, 3.52, 3.92, 4.12, 5.00, 5.24, 5.40, 5.72, 5.92, 6.08, 6.28, 6.52], "tokens":["景", "天", "谂", "唔", "到", "呢", "个", "守", "门", "嘅", "弟", "子", "竟", "然", "咁", "无", "礼", "霎", "时", "间", "面", "色", "都", "变", "埋"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.551 s
Real time factor (RTF): 0.551 / 7.168 = 0.077

yue-6.wav

Wave filename	Content	Ground truth
yue-6.wav		六个星期嘅课程包括六堂课同两个测验你唔掌握到基本嘅十九个声母五十六个韵母同九个声调我哋仲针对咗广东话学习者会遇到嘅大樽颈啊以国语为母语人士最难掌握嘅五大韵母教课书唔会教你嘅七种变音同十种变调说话生硬唔自然嘅根本性问题提供全新嘅学习方向等你突破难关

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-6.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-6.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-6.wav
{"lang": "", "emotion": "", "event": "", "text": "六个星期嘅课程包括六堂课同两个测验你只掌握到基本嘅十九个声母五十六个韵母同九个声调我哋仲针对咗广东话学习者会遇到嘅大樽颈啊以国语为母语人士最难掌握嘅五大韵母教课书唔会教你嘅七种变音同十种变调说话生硬唔自然嘅根本性问题提供全新嘅学习方向等你突破难关", "timestamps": [0.52, 0.68, 0.92, 1.12, 1.32, 1.44, 1.64, 2.20, 2.40, 2.60, 2.80, 3.04, 3.48, 3.68, 3.84, 4.08, 4.28, 4.92, 5.20, 5.36, 5.52, 5.68, 5.92, 6.12, 6.36, 6.64, 6.84, 7.00, 7.12, 7.32, 7.68, 7.88, 8.04, 8.16, 8.28, 8.52, 8.96, 9.20, 9.40, 9.56, 9.72, 10.16, 10.32, 10.48, 10.60, 10.76, 10.92, 11.16, 11.36, 11.56, 11.72, 11.88, 12.08, 12.44, 12.64, 12.84, 13.04, 13.56, 13.80, 14.04, 14.28, 14.68, 14.84, 15.04, 15.24, 15.48, 15.60, 15.76, 15.96, 16.44, 16.68, 16.92, 17.12, 17.32, 17.76, 17.92, 18.08, 18.32, 18.80, 19.08, 19.28, 19.52, 19.68, 19.84, 20.04, 20.20, 20.40, 20.60, 20.84, 21.04, 21.40, 21.64, 21.80, 22.04, 22.20, 23.16, 23.32, 23.56, 23.80, 24.24, 24.44, 24.64, 24.84, 25.24, 25.48, 25.72, 25.92, 26.08, 26.60, 26.76, 27.04, 27.28, 27.44, 27.56, 27.72, 27.88, 28.08, 28.60, 28.76, 29.32, 29.52, 29.76, 29.96], "tokens":["六", "个", "星", "期", "嘅", "课", "程", "包", "括", "六", "堂", "课", "同", "两", "个", "测", "验", "你", "只", "掌", "握", "到", "基", "本", "嘅", "十", "九", "个", "声", "母", "五", "十", "六", "个", "韵", "母", "同", "九", "个", "声", "调", "我", "哋", "仲", "针", "对", "咗", "广", "东", "话", "学", "习", "者", "会", "遇", "到", "嘅", "大", "樽", "颈", "啊", "以", "国", "语", "为", "母", "语", "人", "士", "最", "难", "掌", "握", "嘅", "五", "大", "韵", "母", "教", "课", "书", "唔", "会", "教", "你", "嘅", "七", "种", "变", "音", "同", "十", "种", "变", "调", "说", "话", "生", "硬", "唔", "自", "然", "嘅", "根", "本", "性", "问", "题", "提", "供", "全", "新", "嘅", "学", "习", "方", "向", "等", "你", "突", "破", "难", "关"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 2.590 s
Real time factor (RTF): 2.590 / 30.592 = 0.085

yue-7.wav

Wave filename	Content	Ground truth
yue-7.wav		同意嘅累积唔系阴同阳嘅累积可以讲三既融合咗一同意融合咗阴同阳

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-7.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-7.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-7.wav
{"lang": "", "emotion": "", "event": "", "text": "同意嘅累积唔系阴同阳嘅累积可以讲三既融合咗一同二融合咗阴同阳", "timestamps": [0.64, 0.92, 1.24, 1.40, 1.64, 2.60, 2.80, 3.04, 3.44, 3.76, 4.04, 4.20, 4.40, 5.60, 5.80, 6.08, 6.96, 8.00, 8.24, 8.48, 8.80, 9.36, 9.88, 10.16, 11.28, 11.48, 11.76, 12.16, 12.64, 12.88], "tokens":["同", "意", "嘅", "累", "积", "唔", "系", "阴", "同", "阳", "嘅", "累", "积", "可", "以", "讲", "三", "既", "融", "合", "咗", "一", "同", "二", "融", "合", "咗", "阴", "同", "阳"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.078 s
Real time factor (RTF): 1.078 / 13.900 = 0.078

yue-8.wav

Wave filename	Content	Ground truth
yue-8.wav		而较早前已经复航嘅氹仔北安码头星期五开始增设夜间航班不过两个码头暂时都冇凌晨班次有旅客希望尽快恢复可以留喺澳门长啲时间

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-8.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-8.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-8.wav
{"lang": "", "emotion": "", "event": "", "text": "而较早前已经复航嘅氹仔北安码头星期五开始增设夜间航班不过两个码头暂时都冇凌晨班次有旅客希望尽快恢复可以留喺澳门长啲时间", "timestamps": [0.40, 0.56, 0.76, 0.92, 1.16, 1.28, 1.52, 1.68, 1.92, 2.12, 2.32, 2.52, 2.72, 2.92, 3.12, 3.48, 3.64, 3.80, 3.96, 4.16, 4.48, 4.68, 4.92, 5.08, 5.24, 5.40, 6.24, 6.40, 6.68, 6.84, 7.04, 7.20, 7.44, 7.68, 7.88, 8.04, 8.24, 8.40, 8.60, 8.80, 9.60, 9.80, 9.96, 10.12, 10.28, 10.52, 10.72, 10.88, 11.12, 11.68, 11.80, 11.96, 12.12, 12.32, 12.52, 12.76, 12.96, 13.20, 13.40], "tokens":["而", "较", "早", "前", "已", "经", "复", "航", "嘅", "氹", "仔", "北", "安", "码", "头", "星", "期", "五", "开", "始", "增", "设", "夜", "间", "航", "班", "不", "过", "两", "个", "码", "头", "暂", "时", "都", "冇", "凌", "晨", "班", "次", "有", "旅", "客", "希", "望", "尽", "快", "恢", "复", "可", "以", "留", "喺", "澳", "门", "长", "啲", "时", "间"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.138 s
Real time factor (RTF): 1.138 / 14.080 = 0.081

yue-9.wav

Wave filename	Content	Ground truth
yue-9.wav		刘备仲马鞭一指蜀兵一齐掩杀过去打到吴兵大败唉刘备八路兵马以雷霆万钧之势啊杀到吴兵啊尸横遍野血流成河

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-9.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-9.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-9.wav
{"lang": "", "emotion": "", "event": "", "text": "刘备仲马鞭一指蜀兵一齐掩杀过去打到吴兵大败嘿刘备八路兵马以雷霆万军之势啊杀到吴兵啊尸横遍野血流成河", "timestamps": [0.44, 0.64, 0.80, 1.00, 1.20, 1.36, 1.48, 2.44, 2.64, 2.88, 3.20, 3.44, 3.68, 3.88, 4.04, 4.36, 4.56, 4.80, 5.00, 5.28, 5.48, 6.24, 6.72, 6.96, 7.40, 7.64, 7.84, 8.08, 8.76, 9.00, 9.24, 9.48, 9.68, 9.92, 10.12, 10.28, 10.44, 10.64, 10.84, 11.04, 11.24, 11.80, 12.20, 12.48, 12.76, 13.00, 13.20, 13.40, 13.60], "tokens":["刘", "备", "仲", "马", "鞭", "一", "指", "蜀", "兵", "一", "齐", "掩", "杀", "过", "去", "打", "到", "吴", "兵", "大", "败", "嘿", "刘", "备", "八", "路", "兵", "马", "以", "雷", "霆", "万", "军", "之", "势", "啊", "杀", "到", "吴", "兵", "啊", "尸", "横", "遍", "野", "血", "流", "成", "河"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.116 s
Real time factor (RTF): 1.116 / 14.336 = 0.078

yue-10.wav

Wave filename	Content	Ground truth
yue-10.wav		原来王力宏咧系佢家中里面咧成就最低个吓哇

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-10.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-10.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-10.wav
{"lang": "", "emotion": "", "event": "", "text": "原来王力宏呢系佢家中里边咧成就最低个吓", "timestamps": [0.44, 0.60, 0.92, 1.28, 1.52, 1.68, 1.84, 1.96, 2.20, 2.44, 2.60, 2.76, 2.88, 3.08, 3.32, 3.60, 3.80, 4.20, 5.00], "tokens":["原", "来", "王", "力", "宏", "呢", "系", "佢", "家", "中", "里", "边", "咧", "成", "就", "最", "低", "个", "吓"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.481 s
Real time factor (RTF): 0.481 / 6.656 = 0.072

yue-11.wav

Wave filename	Content	Ground truth
yue-11.wav		无论你提出任何嘅要求

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-11.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-11.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-11.wav
{"lang": "", "emotion": "", "event": "", "text": "无论你提出任何嘅要求", "timestamps": [0.56, 0.68, 0.84, 1.00, 1.16, 1.36, 1.56, 1.72, 1.88, 2.08], "tokens":["无", "论", "你", "提", "出", "任", "何", "嘅", "要", "求"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.225 s
Real time factor (RTF): 0.225 / 2.688 = 0.084

yue-12.wav

Wave filename	Content	Ground truth
yue-12.wav		咁咁多样材料咁我哋首先第一步处理咗一件

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-12.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-12.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-12.wav
{"lang": "", "emotion": "", "event": "", "text": "咁咁多样材料咁我哋首先第一步处理咗一件", "timestamps": [0.52, 0.76, 0.96, 1.16, 1.36, 1.60, 2.00, 2.12, 2.24, 2.36, 2.60, 2.84, 3.00, 3.24, 3.68, 3.88, 4.04, 4.16, 4.28], "tokens":["咁", "咁", "多", "样", "材", "料", "咁", "我", "哋", "首", "先", "第", "一", "步", "处", "理", "咗", "一", "件"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.355 s
Real time factor (RTF): 0.355 / 4.864 = 0.073

yue-13.wav

Wave filename	Content	Ground truth
yue-13.wav		啲点样对于佢哋嘅服务态度啊不透过呢一年左右嘅时间啦其实大家都静一静啦咁你就会见到香港嘅经济其实

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-13.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-13.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-13.wav
{"lang": "", "emotion": "", "event": "", "text": "啲点样对于佢哋嘅服务态度啊当透过呢一年左右嘅时间啦其实大家都静一静啦咁你就会见到香港嘅经济其实", "timestamps": [0.04, 0.24, 0.44, 0.72, 0.88, 1.08, 1.28, 1.88, 2.16, 2.36, 2.60, 2.84, 3.04, 3.32, 3.52, 3.76, 4.04, 4.32, 4.60, 4.80, 5.04, 5.24, 5.36, 5.56, 5.76, 6.16, 6.32, 6.48, 6.68, 6.84, 7.08, 7.24, 7.40, 7.60, 8.08, 8.24, 8.40, 8.52, 8.68, 8.84, 9.04, 9.24, 9.40, 9.52, 9.72, 10.00, 10.20], "tokens":["啲", "点", "样", "对", "于", "佢", "哋", "嘅", "服", "务", "态", "度", "啊", "当", "透", "过", "呢", "一", "年", "左", "右", "嘅", "时", "间", "啦", "其", "实", "大", "家", "都", "静", "一", "静", "啦", "咁", "你", "就", "会", "见", "到", "香", "港", "嘅", "经", "济", "其", "实"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.817 s
Real time factor (RTF): 0.817 / 10.624 = 0.077

yue-14.wav

Wave filename	Content	Ground truth
yue-14.wav		就即刻会同贵正两位八代长老带埋五名七代弟子前啲灵蛇岛想话生擒谢信抢咗屠龙宝刀翻嚟献俾帮主嘅

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-14.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-14.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-14.wav
{"lang": "", "emotion": "", "event": "", "text": "就即刻会同贵正两位八代长老带埋五零七代弟子前啲灵蛇岛想话生擒谢信抢咗屠龙堡都翻嚟献俾帮主嘅", "timestamps": [0.28, 0.40, 0.52, 0.72, 0.96, 1.24, 1.52, 1.80, 1.92, 2.12, 2.32, 2.60, 2.84, 3.72, 3.88, 4.20, 4.44, 4.64, 4.84, 5.08, 5.28, 6.00, 6.12, 6.32, 6.56, 6.84, 7.80, 8.00, 8.36, 8.64, 9.00, 9.24, 10.12, 10.28, 10.52, 10.72, 10.92, 11.12, 11.28, 11.48, 11.76, 11.92, 12.16, 12.40, 12.64], "tokens":["就", "即", "刻", "会", "同", "贵", "正", "两", "位", "八", "代", "长", "老", "带", "埋", "五", "零", "七", "代", "弟", "子", "前", "啲", "灵", "蛇", "岛", "想", "话", "生", "擒", "谢", "信", "抢", "咗", "屠", "龙", "堡", "都", "翻", "嚟", "献", "俾", "帮", "主", "嘅"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.000 s
Real time factor (RTF): 1.000 / 13.056 = 0.077

yue-15.wav

Wave filename	Content	Ground truth
yue-15.wav		我知道我的观众大部分都是对广东话有兴趣想学广东话的人

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-15.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-15.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-15.wav
{"lang": "", "emotion": "", "event": "", "text": "我知道我嘅观众大部分都系对广东话有兴趣想学广东话嘅人", "timestamps": [0.44, 0.56, 0.72, 0.84, 1.00, 1.12, 1.36, 2.08, 2.28, 2.48, 2.68, 2.80, 2.96, 3.12, 3.32, 3.48, 3.64, 3.84, 4.04, 4.80, 5.00, 5.20, 5.40, 5.56, 5.76, 5.92], "tokens":["我", "知", "道", "我", "嘅", "观", "众", "大", "部", "分", "都", "系", "对", "广", "东", "话", "有", "兴", "趣", "想", "学", "广", "东", "话", "嘅", "人"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.453 s
Real time factor (RTF): 0.453 / 6.400 = 0.071

yue-16.wav

Wave filename	Content	Ground truth
yue-16.wav		诶原来啊我哋中国人呢讲究物极必反

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-16.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-16.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-16.wav
{"lang": "", "emotion": "", "event": "", "text": "啊原来啊我哋中国人呢讲究密极必反", "timestamps": [1.80, 1.92, 2.08, 2.24, 2.72, 2.84, 3.00, 3.20, 3.40, 3.56, 3.72, 3.88, 4.08, 4.28, 4.48, 4.76], "tokens":["啊", "原", "来", "啊", "我", "哋", "中", "国", "人", "呢", "讲", "究", "密", "极", "必", "反"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 0.467 s
Real time factor (RTF): 0.467 / 5.700 = 0.082

yue-17.wav

Wave filename	Content	Ground truth
yue-17.wav		如果东边道建成咁丹东呢就会成为最近嘅出海港同埋经过哈大线出海相比绥分河则会减少运渠三百五十六公里

./build/bin/sherpa-onnx-offline \
  --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt \
  --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx \
  --num-threads=1 \
  ./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-17.wav

/Users/fangjun/open-source/sherpa-onnx/sherpa-onnx/csrc/parse-options.cc:Read:372 ./build/bin/sherpa-onnx-offline --tokens=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt --wenet-ctc-model=./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx --num-threads=1 sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-17.wav 

OfflineRecognizerConfig(feat_config=FeatureExtractorConfig(sampling_rate=16000, feature_dim=80, low_freq=20, high_freq=-400, dither=0, normalize_samples=True, snip_edges=False), model_config=OfflineModelConfig(transducer=OfflineTransducerModelConfig(encoder_filename="", decoder_filename="", joiner_filename=""), paraformer=OfflineParaformerModelConfig(model=""), nemo_ctc=OfflineNemoEncDecCtcModelConfig(model=""), whisper=OfflineWhisperModelConfig(encoder="", decoder="", language="", task="transcribe", tail_paddings=-1), fire_red_asr=OfflineFireRedAsrModelConfig(encoder="", decoder=""), tdnn=OfflineTdnnModelConfig(model=""), zipformer_ctc=OfflineZipformerCtcModelConfig(model=""), wenet_ctc=OfflineWenetCtcModelConfig(model="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/model.int8.onnx"), sense_voice=OfflineSenseVoiceModelConfig(model="", language="auto", use_itn=False), moonshine=OfflineMoonshineModelConfig(preprocessor="", encoder="", uncached_decoder="", cached_decoder=""), dolphin=OfflineDolphinModelConfig(model=""), canary=OfflineCanaryModelConfig(encoder="", decoder="", src_lang="", tgt_lang="", use_pnc=True), telespeech_ctc="", tokens="./sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/tokens.txt", num_threads=1, debug=False, provider="cpu", model_type="", modeling_unit="cjkchar", bpe_vocab=""), lm_config=OfflineLMConfig(model="", scale=0.5, lodr_scale=0.01, lodr_fst="", lodr_backoff_id=-1), ctc_fst_decoder_config=OfflineCtcFstDecoderConfig(graph="", max_active=3000), decoding_method="greedy_search", max_active_paths=4, hotwords_file="", hotwords_score=1.5, blank_penalty=0, rule_fsts="", rule_fars="", hr=HomophoneReplacerConfig(dict_dir="", lexicon="", rule_fsts=""))
Creating recognizer ...
Started
Done!

sherpa-onnx-wenetspeech-yue-u2pp-conformer-ctc-zh-en-cantonese-int8-2025-09-10/test_wavs/yue-17.wav
{"lang": "", "emotion": "", "event": "", "text": "如果东边道建城咁丹东呢就会成为最近嘅出海港同埋经过哈大线出海相比绥分河将会减少运距三百五十六公里", "timestamps": [0.52, 0.64, 0.84, 1.04, 1.28, 1.52, 1.80, 2.72, 2.96, 3.20, 3.44, 3.96, 4.08, 4.24, 4.40, 4.60, 4.76, 4.92, 5.08, 5.20, 5.44, 6.48, 6.60, 6.80, 6.96, 7.12, 7.36, 7.56, 7.76, 7.96, 8.16, 8.36, 9.40, 9.60, 9.88, 10.40, 10.52, 10.68, 10.92, 11.16, 11.36, 11.92, 12.16, 12.32, 12.48, 12.64, 12.80, 13.00], "tokens":["如", "果", "东", "边", "道", "建", "城", "咁", "丹", "东", "呢", "就", "会", "成", "为", "最", "近", "嘅", "出", "海", "港", "同", "埋", "经", "过", "哈", "大", "线", "出", "海", "相", "比", "绥", "分", "河", "将", "会", "减", "少", "运", "距", "三", "百", "五", "十", "六", "公", "里"], "words": []}
----
num threads: 1
decoding method: greedy_search
Elapsed seconds: 1.039 s
Real time factor (RTF): 1.039 / 13.800 = 0.075