Repository navigation
Add JavaScript API for FunASR Nano (node-addon) #3026
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| // Copyright (c) 2026 Xiaomi Corporation | ||
| const sherpa_onnx = require('sherpa-onnx-node'); | ||
|
|
||
| // Please download test files from | ||
| // https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models | ||
| const config = { | ||
| 'featConfig': { | ||
| 'sampleRate': 16000, | ||
| 'featureDim': 80, | ||
| }, | ||
| 'modelConfig': { | ||
| 'funasrNano': { | ||
| 'encoderAdaptor': | ||
| './sherpa-onnx-funasr-nano-int8-2025-12-30/encoder_adaptor.int8.onnx', | ||
| 'llm': './sherpa-onnx-funasr-nano-int8-2025-12-30/llm.int8.onnx', | ||
| 'embedding': | ||
| './sherpa-onnx-funasr-nano-int8-2025-12-30/embedding.int8.onnx', | ||
| 'tokenizer': './sherpa-onnx-funasr-nano-int8-2025-12-30/Qwen3-0.6B', | ||
| }, | ||
| 'tokens': '', | ||
| 'numThreads': 2, | ||
| 'provider': 'cpu', | ||
| 'debug': 1, | ||
| } | ||
| }; | ||
|
|
||
| const waveFilename = | ||
| './sherpa-onnx-funasr-nano-int8-2025-12-30/test_wavs/lyrics.wav'; | ||
|
Comment on lines
+6
to
+28
There was a problem hiding this comment. The model directory path is hardcoded in multiple places. To improve maintainability, it's a good practice to define it as a constant and reuse it. This makes it much easier to update the model version in the future. For example: const modelDir = './sherpa-onnx-funasr-nano-int8-2025-12-30';
const config = {
'featConfig': {
'sampleRate': 16000,
'featureDim': 80,
},
'modelConfig': {
'funasrNano': {
'encoderAdaptor': `${modelDir}/encoder_adaptor.int8.onnx`,
'llm': `${modelDir}/llm.int8.onnx`,
'embedding': `${modelDir}/embedding.int8.onnx`,
'tokenizer': `${modelDir}/Qwen3-0.6B`,
},
'tokens': '',
'numThreads': 2,
'provider': 'cpu',
'debug': 1,
}
};
const waveFilename = `${modelDir}/test_wavs/lyrics.wav`; |
||
|
|
||
| const recognizer = new sherpa_onnx.OfflineRecognizer(config); | ||
| console.log('Started') | ||
| let start = Date.now(); | ||
| const stream = recognizer.createStream(); | ||
| const wave = sherpa_onnx.readWave(waveFilename); | ||
| stream.acceptWaveform({sampleRate: wave.sampleRate, samples: wave.samples}); | ||
|
|
||
| recognizer.decode(stream); | ||
| const result = recognizer.getResult(stream); | ||
| let stop = Date.now(); | ||
| console.log('Done') | ||
|
|
||
| const elapsed_seconds = (stop - start) / 1000; | ||
| const duration = wave.samples.length / wave.sampleRate; | ||
| const real_time_factor = elapsed_seconds / duration; | ||
| console.log('Wave duration', duration.toFixed(3), 'seconds') | ||
| console.log('Elapsed', elapsed_seconds.toFixed(3), 'seconds') | ||
| console.log( | ||
| `RTF = ${elapsed_seconds.toFixed(3)}/${duration.toFixed(3)} =`, | ||
| real_time_factor.toFixed(3)) | ||
| console.log(waveFilename) | ||
| console.log('result\n', result) | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
To improve script robustness and maintainability, it's better to chain commands that depend on each other with
&&. This ensures that the script will stop if a command fails. Also, using a variable for the model name avoids repetition and makes it easier to update.Consider adding
set -eat the top of your script to make it exit immediately if a command exits with a non-zero status.