Introduction
Note: You need Node >= 18.
This directory contains nodejs examples for sherpa-onnx.
It uses WebAssembly to wrap sherpa-onnx for NodeJS and it does not support multiple threads.
Note: ../nodejs-addon-examples uses
node-addon-api to wrap
sherpa-onnx for NodeJS and it supports multiple threads.
Before you continue, please first run
cd ./nodejs-examples
npm iIn the following, we describe how to use sherpa-onnx for text-to-speech and speech-to-text.
Speaker diarization
In the following, we demonstrate how to run speaker diarization.
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-segmentation-models/sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
tar xvf sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
rm sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-recongition-models/3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-segmentation-models/0-four-speakers-zh.wav
node ./test-offline-speaker-diarization.jsText-to-speech
In the following, we demonstrate how to run text-to-speech.
./test-offline-tts-matcha-zh.js
./test-offline-tts-matcha-zh.js shows how to use matcha-icefall-zh-baker for text-to-speech.
You can use the following command to run it:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-zh-baker.tar.bz2
tar xvf matcha-icefall-zh-baker.tar.bz2
rm matcha-icefall-zh-baker.tar.bz2
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
node ./test-offline-tts-matcha-zh.js./test-offline-tts-matcha-en.js
./test-offline-tts-matcha-en.js shows how to use matcha-icefall-en_US-ljspeech for text-to-speech.
You can use the following command to run it:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-en_US-ljspeech.tar.bz2
tar xf matcha-icefall-en_US-ljspeech.tar.bz2
rm matcha-icefall-en_US-ljspeech.tar.bz2
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
node ./test-offline-tts-matcha-en.js./test-offline-tts-vits-en.js
./test-offline-tts-vits-en.js shows how to use vits-piper-en_US-amy-low.tar.bz2 for text-to-speech.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
tar xvf vits-piper-en_US-amy-low.tar.bz2
node ./test-offline-tts-vits-en.js./test-offline-tts-vits-zh.js
./test-offline-tts-vits-zh.js shows how to use a VITS pretrained model aishell3 for text-to-speech.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-icefall-zh-aishell3.tar.bz2
tar xvf vits-icefall-zh-aishell3.tar.bz2
node ./test-offline-tts-vits-zh.jsSpeech-to-text
In the following, we demonstrate how to decode files and how to perform
speech recognition with a microphone with nodejs.
./test-offline-nemo-ctc.js
./test-offline-nemo-ctc.js demonstrates how to decode a file with a NeMo CTC model. In the code we use stt_en_conformer_ctc_small.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-ctc-en-conformer-small.tar.bz2
tar xvf sherpa-onnx-nemo-ctc-en-conformer-small.tar.bz2
node ./test-offline-nemo-ctc.js./test-offline-paraformer.js
./test-offline-paraformer.js demonstrates how to decode a file with a non-streaming Paraformer model. In the code we use sherpa-onnx-paraformer-zh-2023-09-14.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
tar xvf sherpa-onnx-paraformer-zh-2023-09-14.tar.bz2
node ./test-offline-paraformer.js./test-offline-sense-voice.js
./test-offline-sense-voice.js demonstrates how to decode a file with a non-streaming Paraformer model.
You can use the following command to run it:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
tar xvf sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
rm sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
node ./test-offline-sense-voice.js./test-offline-transducer.js
./test-offline-transducer.js demonstrates how to decode a file with a non-streaming transducer model. In the code we use sherpa-onnx-zipformer-en-2023-06-26.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-en-2023-06-26.tar.bz2
tar xvf sherpa-onnx-zipformer-en-2023-06-26.tar.bz2
node ./test-offline-transducer.js./test-vad-with-non-streaming-asr-whisper.js
./test-vad-with-non-streaming-asr-whisper.js shows how to use VAD + whisper to decode a very long file.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-whisper-tiny.en.tar.bz2
tar xvf sherpa-onnx-whisper-tiny.en.tar.bz2
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/Obama.wav
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
node ./test-vad-with-non-streaming-asr-whisper.js./test-offline-whisper.js
./test-offline-whisper.js demonstrates how to decode a file with a Whisper model. In the code we use sherpa-onnx-whisper-tiny.en.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-whisper-tiny.en.tar.bz2
tar xvf sherpa-onnx-whisper-tiny.en.tar.bz2
node ./test-offline-whisper.js./test-offline-moonshine.js
./test-offline-moonshine.js demonstrates how to decode a file with a Moonshine model. In the code we use sherpa-onnx-moonshine-tiny-en-int8.
You can use the following command to run it:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
tar xvf sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
node ./test-offline-moonshine.js./test-vad-with-non-streaming-asr-moonshine.js
./test-vad-with-non-streaming-asr-moonshine.js shows how to use VAD + whisper to decode a very long file.
You can use the following command to run it:
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
tar xvf sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/Obama.wav
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
node ./test-vad-with-non-streaming-asr-moonshine.js./test-online-paraformer-microphone.js
./test-online-paraformer-microphone.js demonstrates how to do real-time speech recognition from microphone with a streaming Paraformer model. In the code we use sherpa-onnx-streaming-paraformer-bilingual-zh-en.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2
rm sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2
node ./test-online-paraformer-microphone.js./test-online-paraformer.js
./test-online-paraformer.js demonstrates how to decode a file using a streaming Paraformer model. In the code we use sherpa-onnx-streaming-paraformer-bilingual-zh-en.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2
rm sherpa-onnx-streaming-paraformer-bilingual-zh-en.tar.bz2
node ./test-online-paraformer.js./test-online-transducer-microphone.js
./test-online-transducer-microphone.js demonstrates how to do real-time speech recognition with microphone using a streaming transducer model. In the code we use sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
node ./test-online-transducer-microphone.js./test-online-transducer.js
./test-online-transducer.js demonstrates how to decode a file using a streaming transducer model. In the code we use sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
node ./test-online-transducer.js./test-online-zipformer2-ctc.js
./test-online-zipformer2-ctc.js demonstrates how to decode a file using a streaming zipformer2 CTC model. In the code we use sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
node ./test-online-zipformer2-ctc.js./test-online-zipformer2-ctc-hlg.js
./test-online-zipformer2-ctc-hlg.js demonstrates how to decode a file using a streaming zipformer2 CTC model with HLG. In the code we use sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.
You can use the following command to run it:
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.tar.bz2
tar xvf sherpa-onnx-streaming-zipformer-ctc-small-2024-03-18.tar.bz2
node ./test-online-zipformer2-ctc-hlg.js