JavaScript API with WebAssembly for speaker diarization (#1414)

#1408 uses [node-addon-api](https://github.com/nodejs/node-addon-api) to call C API from JavaScript, whereas this pull request uses WebAssembly to call C API from JavaScript.
This commit is contained in:
Fangjun Kuang
2024-10-11 11:40:10 +08:00
committed by GitHub
parent f1b311ee4f
commit eefc172095
9 changed files with 122 additions and 10 deletions

View File

@@ -12,7 +12,6 @@ Remember to rename the downloaded files.
The following is an example.
```bash
cd wasm/speaker-diarization/assets/
@@ -22,9 +21,6 @@ rm sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
cp sherpa-onnx-pyannote-segmentation-3-0/model.onnx ./segmentation.onnx
rm -rf sherpa-onnx-pyannote-segmentation-3-0
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
mv 3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx ./embedding.onnx
```