EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add JavaScript API for SenseVoice (#1157)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-07-21 10:14:14 +08:00
committed by GitHub
parent 8f4d332aab
commit c3260ef842
6 changed files with 210 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
nodejs-addon-examples/README.md
View File

@@ -95,6 +95,7 @@ The following tables list the examples in this folder.
|[./test_asr_non_streaming_whisper.js](./test_asr_non_streaming_whisper.js)| Non-streaming speech recognition from a file using [Whisper](https://github.com/openai/whisper)|
|[./test_asr_non_streaming_nemo_ctc.js](./test_asr_non_streaming_nemo_ctc.js)|Non-streaming speech recognition from a file using a [NeMo](https://github.com/NVIDIA/NeMo) CTC model with greedy search|
|[./test_asr_non_streaming_paraformer.js](./test_asr_non_streaming_paraformer.js)|Non-streaming speech recognition from a file using [Paraformer](https://github.com/alibaba-damo-academy/FunASR)|
|[./test_asr_non_streaming_sense_voice.js](./test_asr_non_streaming_sense_voice.js)|Non-streaming speech recognition from a file using [SenseVoice](https://github.com/FunAudioLLM/SenseVoice)|
## Non-Streaming speech-to-text from a microphone with VAD
@@ -104,6 +105,7 @@ The following tables list the examples in this folder.
|[./test_vad_asr_non_streaming_whisper_microphone.js](./test_vad_asr_non_streaming_whisper_microphone.js)|VAD + Non-streaming speech recognition from a microphone using [Whisper](https://github.com/openai/whisper)|
|[./test_vad_asr_non_streaming_nemo_ctc_microphone.js](./test_vad_asr_non_streaming_nemo_ctc_microphone.js)|VAD + Non-streaming speech recognition from a microphone using a [NeMo](https://github.com/NVIDIA/NeMo) CTC model with greedy search|
|[./test_vad_asr_non_streaming_paraformer_microphone.js](./test_vad_asr_non_streaming_paraformer_microphone.js)|VAD + Non-streaming speech recognition from a microphone using [Paraformer](https://github.com/alibaba-damo-academy/FunASR)|
|[./test_vad_asr_non_streaming_sense_voice_microphone.js](./test_vad_asr_non_streaming_sense_voice_microphone.js)|VAD + Non-streaming speech recognition from a microphone using [SenseVoice](https://github.com/FunAudioLLM/SenseVoice)|
## Text-to-speech
@@ -252,6 +254,20 @@ npm install naudiodon2
node ./test_vad_asr_non_streaming_paraformer_microphone.js
```
### Non-streaming speech recognition with SenseVoice
```bash
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_asr_non_streaming_sense_voice.js
# To run VAD + non-streaming ASR with Paraformer using a microphone
npm install naudiodon2
node ./test_vad_asr_non_streaming_sense_voice_microphone.js
```
### Text-to-speech with piper VITS models (TTS)
```bash