sherpa-onnx
Hint
During speech recognition, it does not need to access the Internet. Everyting is processed locally on your device.
We support using onnx with onnxruntime to replace PyTorch for neural network computation. The code is put in a separate repository sherpa-onnx.
sherpa-onnx is self-contained and everything can be compiled from source.
Please refer to https://k2-fsa.github.io/icefall/model-export/export-onnx.html for how to export models to onnx format.
In the following, we describe how to build sherpa-onnx for Linux, macOS, Windows, embedded systems, Android, and iOS.
Also, we show how to use it for speech recognition with pre-trained models.
- Tutorials
- Installation
- Frequently Asked Question (FAQs)
- Python
- C API
- Go API
- C# API
- WebAssembly
- Android
- iOS
- WebSocket
- Hotwords (Contextual biasing)
- KWS Open vocabulary keyword spotting (Customized keyword spotting)
- Punctuation
- Audio tagging
- Spoken language identification
- Pre-trained models
- Online transducer models
- Zipformer-transducer-based Models
- sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12 (Chinese)
- pkufool/icefall-asr-zipformer-streaming-wenetspeech-20230615 (Chinese)
- csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-26 (English)
- csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-21 (English)
- csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-02-21 (English)
- csukuangfj/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20 (Bilingual, Chinese + English)
- shaojieli/sherpa-onnx-streaming-zipformer-fr-2023-04-14 (French)
- sherpa-onnx-streaming-zipformer-small-bilingual-zh-en-2023-02-16 (Bilingual, Chinese + English)
- csukuangfj/sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23 (Chinese)
- csukuangfj/sherpa-onnx-streaming-zipformer-en-20M-2023-02-17 (English)
- Conformer-transducer-based Models
- LSTM-transducer-based Models
- Zipformer-transducer-based Models
- Online paraformer models
- Online CTC models
- Offline transducer models
- Zipformer-transducer-based Models
- sherpa-onnx-zipformer-cantonese-2024-03-13 (Cantonese, 粤语)
- sherpa-onnx-zipformer-gigaspeech-2023-12-12 (English)
- zrjin/sherpa-onnx-zipformer-multi-zh-hans-2023-9-2 (Chinese)
- yfyeung/icefall-asr-cv-corpus-13.0-2023-03-09-en-pruned-transducer-stateless7-2023-04-17 (English)
- pkufool/icefall-asr-zipformer-wenetspeech-20230615 (Chinese)
- csukuangfj/sherpa-onnx-zipformer-large-en-2023-06-26 (English)
- csukuangfj/sherpa-onnx-zipformer-small-en-2023-06-26 (English)
- csukuangfj/sherpa-onnx-zipformer-en-2023-06-26 (English)
- icefall-asr-multidataset-pruned_transducer_stateless7-2023-05-04 (English)
- csukuangfj/sherpa-onnx-zipformer-en-2023-04-01 (English)
- csukuangfj/sherpa-onnx-zipformer-en-2023-03-30 (English)
- Conformer-transducer-based Models
- Zipformer-transducer-based Models
- Offline paraformer models
- Paraformer models
- csukuangfj/sherpa-onnx-paraformer-trilingual-zh-cantonese-en (Chinese + English + Cantonese 粤语)
- csukuangfj/sherpa-onnx-paraformer-en-2024-03-09 (English)
- csukuangfj/sherpa-onnx-paraformer-zh-small-2024-03-09 (Chinese + English)
- csukuangfj/sherpa-onnx-paraformer-zh-2024-03-09 (Chinese + English)
- csukuangfj/sherpa-onnx-paraformer-zh-2023-03-28 (Chinese + English)
- csukuangfj/sherpa-onnx-paraformer-zh-2023-09-14 (Chinese + English))
- Paraformer models
- Offline CTC models
- Whisper
- WeNet
- Small models
- Online transducer models
- Text-to-speech (TTS)
- Huggingface space
- Pre-trained models
- vits
- All models in a single table
- ljspeech (English, single-speaker)
- VCTK (English, multi-speaker, 109 speakers)
- csukuangfj/vits-zh-hf-fanchen-C (Chinese, 187 speakers)
- csukuangfj/vits-zh-hf-fanchen-wnj (Chinese, 1 male)
- csukuangfj/vits-zh-hf-theresa (Chinese, 804 speakers)
- csukuangfj/vits-zh-hf-eula (Chinese, 804 speakers)
- aishell3 (Chinese, multi-speaker, 174 speakers)
- en_US-lessac-medium (English, single-speaker)
- vits
- WebAssembly
- Piper
- MMS
- Frequently Asked Question (FAQs)