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

Add WebAssembly for NodeJS. (#628)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-03-03 20:00:36 +08:00
committed by GitHub
parent ac6825ff11
commit ed06ced16f
39 changed files with 1450 additions and 1887 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
nodejs-examples/README.md
View File

@@ -2,38 +2,18 @@
This directory contains nodejs examples for [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx).
Before you continue, please first install the npm package `sherpa-onnx` by
Before you continue, please first run
```bash
npm install sherpa-onnx
cd ./nodejs-examples
npm i
```
In the following, we describe how to use [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx)
for text-to-speech and speech-to-text.
**Caution**: If you get the following error:
```
/Users/fangjun/open-source/sherpa-onnx/nodejs-examples/node_modules/ffi-napi/lib/dynamic_library.js:67
if (match = err.match(/^(([^ \t()])+\.so([^ \t:()])*):([ \t])*/)) {
^
TypeError: Cannot read properties of null (reading 'match')
at new DynamicLibrary (/Users/fangjun/open-source/sherpa-onnx/nodejs-examples/node_modules/ffi-napi/lib/dynamic_library.js:67:21)
at Object.Library (/Users/fangjun/open-source/sherpa-onnx/nodejs-examples/node_modules/ffi-napi/lib/library.js:47:10)
at Object.<anonymous> (/Users/fangjun/open-source/sherpa-onnx/nodejs-examples/node_modules/sherpa-onnx3/index.js:268:28)
at Module._compile (node:internal/modules/cjs/loader:1376:14)
at Module._extensions..js (node:internal/modules/cjs/loader:1435:10)
at Module.load (node:internal/modules/cjs/loader:1207:32)
at Module._load (node:internal/modules/cjs/loader:1023:12)
at Module.require (node:internal/modules/cjs/loader:1235:19)
at require (node:internal/modules/helpers:176:18)
at Object.<anonymous> (/Users/fangjun/open-source/sherpa-onnx/nodejs-examples/test-offline-tts-zh.js:3:21)
```
Please downgrade your node to version v13.14.0. See also
https://github.com/node-ffi-napi/node-ffi-napi/issues/244
and
https://github.com/node-ffi-napi/node-ffi-napi/issues/97 .
Note: You need `Node >= 18`.
# Text-to-speech
@@ -71,13 +51,7 @@ node ./test-offline-tts-zh.js
# Speech-to-text
In the following, we demonstrate how to decode files and how to perform
speech recognition with a microphone with `nodejs`. We need to install two additional
npm packages:
```bash
npm install wav naudiodon2
```
speech recognition with a microphone with `nodejs`.
## ./test-offline-nemo-ctc.js
@@ -200,60 +174,3 @@ wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherp
tar xvf sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
node ./test-online-zipformer2-ctc.js
```
## ./test-vad-microphone-offline-paraformer.js
[./test-vad-microphone-offline-paraformer.js](./test-vad-microphone-offline-paraformer.js)
demonstrates how to use [silero-vad](https://github.com/snakers4/silero-vad)
with non-streaming Paraformer for speech recognition from microphone.
You can use the following command to run it:
```bash
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
tar xvf sherpa-onnx-paraformer-zh-2023-03-28.tar.bz2
node ./test-vad-microphone-offline-paraformer.js
```
## ./test-vad-microphone-offline-transducer.js
[./test-vad-microphone-offline-transducer.js](./test-vad-microphone-offline-transducer.js)
demonstrates how to use [silero-vad](https://github.com/snakers4/silero-vad)
with a non-streaming transducer model for speech recognition from microphone.
You can use the following command to run it:
```bash
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
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-vad-microphone-offline-transducer.js
```
## ./test-vad-microphone-offline-whisper.js
[./test-vad-microphone-offline-whisper.js](./test-vad-microphone-offline-whisper.js)
demonstrates how to use [silero-vad](https://github.com/snakers4/silero-vad)
with whisper for speech recognition from microphone.
You can use the following command to run it:
```bash
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
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-vad-microphone-offline-whisper.js
```
## ./test-vad-microphone.js
[./test-vad-microphone.js](./test-vad-microphone.js)
demonstrates how to use [silero-vad](https://github.com/snakers4/silero-vad).
You can use the following command to run it:
```bash
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
node ./test-vad-microphone.js
```