sherpa

• Introduction
• Download pdf
• Social groups
  • WeChat
  • QQ
  • Bilibili (B 站)
  • YouTube
• Run Next-gen Kaldi in your browser
  • Visit our Huggingface space
  • YouTube Video
  • Other Huggingface spaces
• Pre-trained models
  • Pre-trained models for different projects
  • How to download

k2-fsa/sherpa

• sherpa
  • Installation
    • From pre-compiled wheels
      • Linux (CPU)
      • macOS (CPU)
      • Linux (CUDA)
    • From source
      • Install dependencies
      • For general users
      • For developers and advanced users
    • Check your installation
    • Where to get help
  • Pre-trained models
    • Offline CTC models
      • icefall
        • icefall-asr-gigaspeech-conformer-ctc (English)
        • icefall-asr-librispeech-conformer-ctc-jit-bpe-500-2021-11-09 (English)
        • icefall-asr-tedlium3-conformer-ctc2 (English)
        • icefall_asr_librispeech_conformer_ctc (English)
        • icefall_asr_aishell_conformer_ctc (Chinese)
        • icefall-asr-mgb2-conformer_ctc-2022-27-06 (Arabic)
      • WeNet
        • wenet-english-model (English)
        • wenet-chinese-model (Chinese)
      • torchaudio
        • wav2vec2_asr_base (English)
        • voxpopuli_asr_base (German)
      • NeMo
        • sherpa-nemo-ctc-en-citrinet-512 (English)
        • sherpa-nemo-ctc-zh-citrinet-512 (Chinese)
        • sherpa-nemo-ctc-zh-citrinet-1024-gamma-0-25 (Chinese)
        • sherpa-nemo-ctc-de-citrinet-1024 (German)
        • sherpa-nemo-ctc-en-conformer-small (English)
        • sherpa-nemo-ctc-en-conformer-medium (English)
        • sherpa-nemo-ctc-en-conformer-large (English)
        • sherpa-nemo-ctc-de-conformer-large (German)
        • How to convert NeMo models to sherpa
    • Offline transducer models
      • icefall
        • English
        • Chinese
        • Chinese + English
        • Tibetan
    • Online transducer models
      • icefall
        • English
        • Chinese
        • Chinese + English (all-in-one)

k2-fsa/sherpa-ncnn

• sherpa-ncnn
  • Tutorials
    • 中文资料 (Chinese tutorials)
      • Sherpa-ncnn (Windows電腦抓取麥克風聲音即時轉錄文字)
      • 2024 Android整合SherpaNcnn实现离线语音识别（支持中文，手把手带你从编译动态库开始）
      • 2024 在Unity环境下，借助sherpa-ncnn框架，实现实时并准确的中英双语语音识别功能
      • 2024-02-22【RV1126】移植sherpa实时语音识别和TTS文字转语音功能
      • 2023-12-31 离线语音识别 sherpa-ncnn 尝鲜体验
      • 2023-04-26【RV1126】移植kaldi实时语音识别
      • 2023-02-19 离线语音识别库sherpa-ncnn安装和简单测试笔记
  • Installation
    • Installation videos
      • Window (64-bit)
    • Linux
    • macOS
    • Windows
      • 64-bit Windows (x64)
      • 32-bit Windows (x86)
    • Embedded Linux (arm)
      • Install toolchain
      • Build sherpa-ncnn
    • Embedded Linux (aarch64)
      • Install toolchain
      • Build sherpa-ncnn
      • sherpa-ncnn-alsa
    • Embedded Linux (riscv64)
      • Install toolchain
      • Build sherpa-ncnn
  • Python API
    • Installation
      • Method 1
      • Method 2
      • Method 3
      • Method 4 (For developers and embedded boards)
    • Real-time recognition with a microphone
      • 1. Import the required packages
      • 2. Create the recognizer
      • 3. Start recording
      • 4. Read audio samples from the microphone
      • 5. Invoke the recognizer with audio samples
      • 6. Get the recognition result
      • Summary
    • Recognize a file
  • WebAssembly
    • Install Emscripten
    • Build
    • Use pre-built WebAssembly library
      • Download
    • Huggingface Spaces (WebAssembly)
      • English only
      • Chinese + English
  • C API
    • Generate required files
      • Build shared libraries
      • Build static libraries
    • Build decode-file-c-api.c with generated files
  • Endpointing
    • Rule 1
    • Rule 2
    • Rule 3
    • Demo
      • Multilingual (Chinese + English)
    • FAQs
      • How to compute duration of silence
  • Android
    • Video demos
      • Video 1: Chinese
      • Video 2: Chinese + English
      • Video 3: Chinese with background noise
      • Video 4: Chinese poem with background music
    • Build sherpa-ncnn for Android
      • Install Android Studio
      • Download sherpa-ncnn
      • Install NDK
      • Build sherpa-ncnn (C++ code)
        • Build for arm64-v8a
        • Build for armeabi-v7a
        • Build for x86_64
        • Build for x86
      • Download pre-trained models
      • Generate APK
      • Analyze the APK
  • iOS
    • Video demos
      • Video 1: Chinese + English on iPhone 14 Pro (simulator)
      • Video 2: Chinese + English on iPad 11 Pro (simulator)
    • Build sherpa-ncnn for iOS
      • Requirement
      • Download sherpa-ncnn
      • Build sherpa-ncnn (in commandline, C++ Part)
      • Build sherpa-ncnn (in Xcode)
      • Run sherpa-ncnn on your iPhone/iPad
    • For the more curious
      • Files generated by running ./build-ios.sh
        • openmp.xcframework
        • sherpa-ncnn.xcframework
      • How to use files generated by ./build-ios.sh in Xcode
  • Pre-trained models
    • Small models
    • Zipformer-transducer-based Models
      • marcoyang/sherpa-ncnn-streaming-zipformer-zh-14M-2023-02-23 (Chinese)
        • Download the model
        • Decode a single wave file
        • Real-time speech recognition from a microphone
      • marcoyang/sherpa-ncnn-streaming-zipformer-20M-2023-02-17 (English)
        • Download the model
        • Decode a single wave file
        • Real-time speech recognition from a microphone
      • csukuangfj/sherpa-ncnn-streaming-zipformer-en-2023-02-13 (English)
        • Download the model
        • Decode a single wave file
        • Real-time speech recognition from a microphone
      • csukuangfj/sherpa-ncnn-streaming-zipformer-bilingual-zh-en-2023-02-13 (Bilingual, Chinese + English)
        • Download the model
        • Decode a single wave file
        • Real-time speech recognition from a microphone
      • csukuangfj/sherpa-ncnn-streaming-zipformer-small-bilingual-zh-en-2023-02-16 (Bilingual, Chinese + English)
        • Download the model
        • Decode a single wave file
        • Real-time speech recognition from a microphone
        • A faster model of sherpa-ncnn-streaming-zipformer-small-bilingual-zh-en-2023-02-16
      • shaojieli/sherpa-ncnn-streaming-zipformer-fr-2023-04-14
        • Download the model
        • Real-time speech recognition from a microphone
    • LSTM-transducer-based Models
      • marcoyang/sherpa-ncnn-lstm-transducer-small-2023-02-13 (Bilingual, Chinese + English)
        • Decode a single wave file with ./build/bin/sherpa-ncnn
      • csukuangfj/sherpa-ncnn-2022-09-05 (English)
      • csukuangfj/sherpa-ncnn-2022-09-30 (Chinese)
    • Conv-Emformer-transducer-based Models
      • marcoyang/sherpa-ncnn-conv-emformer-transducer-small-2023-01-09 (English)
        • Decode a single wave file with ./build/bin/sherpa-ncnn
        • Decode a single wave file with ./build/bin/sherpa-ncnn (with int8 quantization)
      • csukuangfj/sherpa-ncnn-conv-emformer-transducer-2022-12-06 (Chinese + English)
        • Decode a single wave file with ./build/bin/sherpa-ncnn
        • Real-time speech recognition from a microphone with build/bin/sherpa-ncnn-microphone
      • csukuangfj/sherpa-ncnn-conv-emformer-transducer-2022-12-08 (Chinese)
        • Decode a single wave file with ./build/bin/sherpa-ncnn
        • Real-time speech recognition from a microphone with build/bin/sherpa-ncnn-microphone
      • csukuangfj/sherpa-ncnn-conv-emformer-transducer-2022-12-04 (English)
        • Decode a single wave file with ./build/bin/sherpa-ncnn
        • Real-time speech recognition from a microphone with build/bin/sherpa-ncnn-microphone
  • Examples
    • Raspberry Pi 3B E14
      • Board info
      • OS release
      • lscpu
      • cpuinfo
      • RTF (1 thread)
      • RTF (2 threads)
    • Jetson Nano
      • Board info
      • RTF (4 threads)
    • Jetson NX
      • Board info
      • RTF (2 threads)
      • RTF (4 threads)
      • RTF (6 threads)
    • VisionFive 2
      • Board info
      • RTF (4 threads)
      • Real-time speech recognition with a microphone
  • FAQs
    • Where to get help
    • No default input device found

k2-fsa/sherpa-onnx

• sherpa-onnx
  • Tutorials
    • 中文资料 (Chinese tutorials)
      • 2024-10-09【基于sherpa的本地智能语音助手入门-Java Api版
      • 2024-07-03【🆓 語音辨識引擎sherpa-onnx CPU上篇】讓您輕鬆體驗語音辨識功能(Docker架設)
      • 2024-06-10 SherpaOnnxTtsEngine - Android 本地 TTS 语言转文本引擎
      • 2024-06-10 用LLM搭建100个应用（一）：从0到1搭建自己的Windows贾维斯(1)
      • 2024-05-09 记录一下sherpa-onnx的安装及使用
      • 2024-04-09 rv1106&rv1109&rv1126移植sherpa-onnx 实现离线TTS功能
      • 2023-08-08 snowboy+新一代kaldi（k2-fsa）sherpa-onnx实现离线语音识别【语音助手】
      • 2023-03-16 k2语音识别：如何使用sherpa-onnx
  • Installation
    • Linux
    • macOS
    • Windows
      • 64-bit Windows (x64)
      • 32-bit Windows (x86)
    • Embedded Linux (aarch64)
      • Install toolchain
      • Build sherpa-onnx
      • sherpa-onnx-alsa
      • How to build static libraries and static linked binaries
    • Embedded Linux (arm)
      • Install toolchain
      • Build sherpa-onnx
      • How to build static libraries and static linked binaries
    • Embedded Linux (riscv64)
      • Install toolchain
      • Build sherpa-onnx
      • qemu
        • Run speech-to-text with qemu
        • Run text-to-speech with qemu
  • Frequently Asked Question (FAQs)
    • 在线、离线、流式、非流式的区别
    • Cannot open shared library libasound_module_conf_pulse.so
    • TTS 中文模型没有声音
    • ./gitcompile: line 89: libtoolize: command not found
    • OSError: PortAudio library not found
    • imports github.com/k2-fsa/sherpa-onnx-go-linux: build constraints exclude all Go files
    • External buffers are not allowed
    • The given version [17] is not supported, only version 1 to 10 is supported in this build
  • Python
    • Install the Python Package
      • Method 1 (From pre-compiled wheels, CPU only)
      • Method 2 (From pre-compiled wheels, CPU + CUDA)
      • Method 3 (From source)
      • Method 4 (For developers)
      • Check your installation
    • Decode files
      • Streaming zipformer
      • Non-streaming zipformer
      • Non-streaming paraformer
    • Real-time speech recognition from a microphone
      • With endpoint detection
      • Without endpoint detection
    • Speech recognition from URLs
      • Decode a URL
      • RTMP
        • Install the server
        • Start the server
        • Start ffmpeg to push audio stream
        • Start sherpa-onnx to pull audio stream
    • Streaming WebSocket Server
      • Start the server
        • Use Python API
        • Use a browser
      • colab
    • Non-Streaming WebSocket Server
      • Non-streaming transducer
        • Start the server
        • Start the client
      • Non-streaming paraformer
        • Start the server
        • Start the client
      • Non-streaming CTC model from NeMo
        • Start the server
        • Start the client
      • Non-streaming Whisper tiny.en
        • Start the server
        • Start the client
      • colab
  • C API
    • Generate required files
      • Build shared libraries
      • Build static libraries
    • Build decode-file-c-api.c with generated files
    • colab
  • Java API
    • Build JNI interface (macOS)
      • Setup the environment
      • Build sherpa-onnx
      • Download pre-built JNI libs
    • Build JNI interface (Linux)
      • Setup the environment
      • Build sherpa-onnx
      • Download pre-built JNI libs
    • Build JNI interface (Windows)
      • Download pre-built JNI libs
    • Build the jar package
      • Download pre-built jar
    • Examples
  • Javascript API
    • Install
    • Examples
  • Kotlin API
    • Build JNI interface
    • Examples
  • Swift API
    • Build
    • Examples
  • Go API
    • Decode files with non-streaming models
      • Non-streaming transducer
      • Non-streaming paraformer
      • Non-streaming CTC model from NeMo
    • Decode files with streaming models
      • Streaming transducer
    • Real-time speech recognition from microphone
      • Streaming transducer
    • colab
  • C# API
    • Decode files with non-streaming models
      • Non-streaming transducer
      • Non-streaming paraformer
      • Non-streaming CTC model from NeMo
    • Decode files with streaming models
      • Streaming transducer
    • Real-time speech recognition from microphone
      • Streaming transducer
    • colab
  • Pascal API
    • Install free pascal
    • Build sherpa-onnx
    • Non-streaming speech recognition from files
    • Colab notebook
  • Lazarus
    • Pre-built APPs using Lazarus
    • Generate subtitles
      • Screenshots on different platforms
      • Get sherpa-onnx libraries
        • 1. Build sherpa-onnx from source
        • 2. Download pre-built libraries
      • Build the generate_subtitles project
      • Download models
        • Download the VAD model
        • Download a speech recognition model
        • 1. Wisper
        • 2. Zipformer transducer
        • 3. NeMo transducer
        • 4. SenseVoice
        • 5. Paraformer
        • 6. TeleSpeech
        • 7. Moonshine
      • For the more curious
  • WebAssembly
    • Install Emscripten
    • Build
    • Huggingface Spaces (WebAssembly)
      • English only (Zipformer)
      • Chinese + English (Zipformer)
      • Chinese + English (Paraformer)
      • Chinese + English + Cantonese (Paraformer)
  • Android
    • Pre-built APKs
    • Build sherpa-onnx for Android
      • Install Android Studio
      • Download sherpa-onnx
      • Install NDK
      • Build sherpa-onnx (C++ code)
        • Build for arm64-v8a
        • Build for armv7-eabi
        • Build for x86_64
        • Build for x86
      • Download pre-trained models
      • Generate APK
      • Analyze the APK
  • HarmonyOS
    • Pre-built HAPs
    • On-device speaker identification (本地说话人识别)
      • Open the project with DevEco Studio
      • Select a model
        • Use 3dspeaker_speech_eres2net_base_200k_sv_zh-cn_16k-common.onnx
    • On-device text-to-speech (TTS)
      • Open the project with DevEco Studio
      • Select a text-to-speech model
        • Use vits-melo-tts-zh_en
        • Use vits-piper-en_US-libritts_r-medium
    • On-device VAD + ASR
      • Open the project with DevEco Studio
      • Download a VAD model
      • Select a non-streaming ASR model
        • Use sherpa-onnx-moonshine-tiny-en-int8
        • Use sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17
    • How to build sherpa_onnx.har
      • Download commandline-tools
      • Build sherpa-onnx for HarmonyOS
      • Build sherpa_onnx.har
        • From the command-line
        • Use DevEco Studio
      • Use sherpa_onnx.har in your project
      • Colab demo
  • iOS
    • Build sherpa-onnx for iOS
      • Requirement
      • Download sherpa-onnx
      • Build sherpa-onnx (in commandline, C++ Part)
      • Build sherpa-onnx (in Xcode)
      • Run sherpa-onnx on your iPhone/iPad
  • Flutter
    • Pre-built Flutter Apps
      • Text to speech (TTS, Speech synthesis)
      • Streaming Speech recognition (STT, ASR)
  • WebSocket
    • Streaming WebSocket server and client
      • Build sherpa-onnx with WebSocket support
      • View the server usage
      • Start the server
      • View the usage of the client (C++)
      • Start the client (C++)
      • View the usage of the client (Python)
      • Start the client (Python)
      • Start the client (Python, with microphone)
    • Non-streaming WebSocket server and client
      • Build sherpa-onnx with WebSocket support
      • View the server usage
      • Start the server
        • Start the server with a transducer model
        • Start the server with a paraformer model
      • Start the client (Python)
        • offline-websocket-client-decode-files-paralell.py
        • offline-websocket-client-decode-files-sequential.py
  • Hotwords (Contextual biasing)
    • What are hotwords
    • How do we implement it with an Aho-corasick
    • How to use hotwords in sherpa-onnx
      • Modeling unit is bpe
        • C++ api
        • Python api
      • Modeling unit is cjkchar
        • C++ api
        • Python api
      • Modeling unit is cjkchar+bpe
        • C++ api
        • Python api
  • Keyword spotting
    • What is open vocabulary keyword spotting
    • Decoder for open vocabulary keyword spotting
    • Keywords file
    • How to use keyword spotting in sherpa-onnx
      • command-line tool
    • Android application
    • Pretrained models
  • Punctuation
    • Pre-trained models
      • sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12
        • Download the model
        • C++ binary examples
        • Python API examples
        • Huggingface space examples
        • Video demos
  • Audio tagging
    • Pre-trained models
      • sherpa-onnx-zipformer-small-audio-tagging-2024-04-15
        • Download the model
        • C++ binary examples
        • Python API examples
        • Huggingface space
    • Android
    • WearOS
  • Spoken language identification
    • Pre-trained models
      • whisper
        • Download the model
        • Download test waves
        • Test with Python APIs
        • Android APKs
        • Huggingface space
  • VAD
  • Pre-trained models
    • Online transducer models
      • Zipformer-transducer-based Models
        • sherpa-onnx-streaming-zipformer-korean-2024-06-16 (Korean)
        • sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12 (Chinese)
        • k2-fsa/icefall-asr-zipformer-wenetspeech-streaming-small (Chinese)
        • k2-fsa/icefall-asr-zipformer-wenetspeech-streaming-large (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
        • csukuangfj/sherpa-onnx-streaming-conformer-zh-2023-05-23 (Chinese)
      • LSTM-transducer-based Models
        • csukuangfj/sherpa-onnx-lstm-en-2023-02-17 (English)
        • csukuangfj/sherpa-onnx-lstm-zh-2023-02-20 (Chinese)
    • Online paraformer models
      • Paraformer models
        • csukuangfj/sherpa-onnx-streaming-paraformer-bilingual-zh-en (Chinese + English)
        • csukuangfj/sherpa-onnx-streaming-paraformer-trilingual-zh-cantonese-en (Chinese + Cantonese + English)
    • Online CTC models
      • Zipformer-CTC-based Models
        • sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13 (Chinese)
    • Offline transducer models
      • Zipformer-transducer-based Models
        • sherpa-onnx-zipformer-ru-2024-09-18 (Russian, 俄语)
        • sherpa-onnx-small-zipformer-ru-2024-09-18 (Russian, 俄语)
        • sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01 (Japanese, 日语)
        • sherpa-onnx-zipformer-korean-2024-06-24 (Korean, 韩语)
        • sherpa-onnx-zipformer-thai-2024-06-20 (Thai, 泰语)
        • 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)
        • k2-fsa/icefall-asr-zipformer-wenetspeech-small (Chinese)
        • k2-fsa/icefall-asr-zipformer-wenetspeech-large (Chinese)
        • 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
        • csukuangfj/sherpa-onnx-conformer-zh-stateless2-2023-05-23 (Chinese)
        • csukuangfj/sherpa-onnx-conformer-zh-2023-05-23 (Chinese)
        • csukuangfj/sherpa-onnx-conformer-en-2023-03-18 (English)
      • NeMo transducer-based Models
        • sherpa-onnx-nemo-transducer-giga-am-russian-2024-10-24 (Russian, 俄语)
    • 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))
    • Offline CTC models
      • NeMo
        • How to export models from NeMo to sherpa-onnx
        • English
        • Russian
      • yesno
        • Decode wave files
    • TeleSpeech
      • How to export models from Tele-AI/TeleSpeech-ASR to sherpa-onnx
        • Step 1: Export model.onnx
        • Step 2: Add metadata
        • Step 3: Obtain tokens.txt
      • Models
        • sherpa-onnx-telespeech-ctc-int8-zh-2024-06-04 (支持非常多种方言)
    • Whisper
      • Export Whisper to ONNX
        • Available models
        • Export to onnx
      • tiny.en
        • Real-time factor (RTF) on Raspberry Pi 4 Model B
      • large-v3
        • Run with CPU (float32)
        • Run with CPU (int8)
        • Run with GPU (float32)
        • Run with GPU (int8)
        • colab
      • colab
        • Non-large models
        • Large models
      • Huggingface space
    • WeNet
      • How to export models from WeNet to sherpa-onnx
        • Export for non-streaming inference
        • Export for streaming inference
        • FAQs
        • sherpa-onnx/csrc/online-wenet-ctc-model.cc:Init:144 head does not exist in the metadata
      • All models from WeNet
        • Colab
    • Small models
  • Moonshine
    • Huggingface space
    • Models
      • sherpa-onnx-moonshine-tiny-en-int8
        • Decode wave files
        • Speech recognition from a microphone
        • Speech recognition from a microphone with VAD
      • sherpa-onnx-moonshine-base-en-int8
        • Decode wave files
        • Speech recognition from a microphone
        • Speech recognition from a microphone with VAD
    • Android APKs for Moonshine
    • C API examples
    • C# API examples
    • Dart API examples
    • Go API examples
    • Java API examples
    • JavaScript API examples
      • WebAssembly based npm package
      • node-addon based npm package
    • Kotlin API examples
    • Pascal API examples
    • Python API examples
    • Swift API examples
  • SenseVoice
    • Huggingface space
    • Export SenseVoice to sherpa-onnx
      • The code
      • Test the exported model
      • Where to find exported models
    • Pre-trained Models
      • sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17
        • Download
        • Decode a file with model.onnx
        • Speech recognition from a microphone
        • Speech recognition from a microphone with VAD
    • C API for SenseVoice
      • Explanations
        • 1. Download sherpa-onnx
        • 2. Download the model
        • 3. Build sherpa-onnx
        • 4. View the build result
        • 5. Build the C API example
        • 6. Run it
        • 7. Where to find sense-voice-c-api.c
    • Dart API for SenseVoice
      • Explanations
        • 1. Download the code
        • 2. Download the sherpa-onnx package
        • 3. Run it
    • Python API for SenseVoice
      • Decode a file
      • Speech recognition from a microphone
      • Generate subtitles
        • Chinese
        • English
      • WebSocket server and client example
        • 1. Start the server
        • 2. Start the client (decode files sequentially)
        • 3. Start the client (decode files in parallel)
        • 4. Start the Web browser client
  • Speaker Diarization
    • Pre-trained models
      • Colab notebook
      • sherpa-onnx-pyannote-segmentation-3-0
        • Download the model
        • Usage for speaker diarization
      • sherpa-onnx-reverb-diarization-v1
        • Download the model
        • Usage for speaker diarization
    • Hugginface space for speaker diarization
    • Android APKs for speaker diarization
    • C API examples
    • C++ API examples
    • C# API examples
    • Dart API examples
    • Go API examples
    • Java API examples
    • JavaScript API examples
      • WebAssembly based npm package
      • node-addon based npm package
    • Kotlin API examples
    • Pascal API examples
    • Python API examples
    • Rust API examples
    • Swift API examples
  • Speaker Identification
  • Text-to-speech (TTS)
    • Huggingface space
    • Pre-trained models
      • vits
        • All models in a single table
        • vits-melo-tts-zh_en (Chinese + English, 1 speaker)
        • vits-piper-en_US-glados (English, 1 speaker)
        • vits-piper-en_US-libritts_r-medium (English, 904 speakers)
        • ljspeech (English, single-speaker)
        • VCTK (English, multi-speaker, 109 speakers)
        • csukuangfj/sherpa-onnx-vits-zh-ll (Chinese, 5 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)
    • WebAssembly
      • Install Emscripten
      • Build
      • Huggingface Spaces (WebAssembly)
        • English TTS
        • German TTS
    • Piper
      • Install dependencies
      • Find the pre-trained model from piper
      • Download the pre-trained model
      • Add meta data to the onnx model
      • Download espeak-ng-data
      • Test your converted model
    • MMS
      • Install dependencies
      • Download the model file
      • Download MMS source code
      • Convert the model
      • Use the converted model
    • Frequently Asked Question (FAQs)
      • Is there a colab notebook
      • How to enable UTF-8 on Windows
      • How to install sherpa-onnx for TTS
        • For Python users
        • Build from source
      • Where to get pre-trained TTS models
      • How to handle OOVs

Triton

• Triton
  • Installation
    • Build Triton Image
    • Launch a inference container
  • Triton-server
    • Deploy streaming ASR models with Onnx
    • Deploy offline ASR models with torchscript
  • Triton-client
    • Send requests using client
    • Decode manifests
  • Perf Analyzer
    • Generate Input Data from Audio Files
    • Test Throughput using Perf Analyzer
  • TensorRT acceleration
    • Preparation
    • Model export
    • Benchmark for Conformer TRT encoder vs ONNX