-
Notifications
You must be signed in to change notification settings - Fork 424
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
JavaScript API (node-addon) for speaker diarization (#1408)
- Loading branch information
1 parent
a45e5db
commit 67349b5
Showing
11 changed files
with
443 additions
and
13 deletions.
There are no files selected for viewing
This file contains 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 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 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 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 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 +1,62 @@ | ||
| // Copyright (c) 2024 Xiaomi Corporation | ||
| const sherpa_onnx = require('sherpa-onnx-node'); | ||
|
|
||
| // clang-format off | ||
| /* Please use the following commands to download files | ||
| used in this script | ||
| 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 | ||
| */ | ||
| // clang-format on | ||
|
|
||
| const config = { | ||
| segmentation: { | ||
| pyannote: { | ||
| model: './sherpa-onnx-pyannote-segmentation-3-0/model.onnx', | ||
| }, | ||
| }, | ||
| embedding: { | ||
| model: './3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx', | ||
| }, | ||
| clustering: { | ||
| // since we know that the test wave file | ||
| // ./0-four-speakers-zh.wav contains 4 speakers, we use 4 for numClusters | ||
| // here. if you don't have such information, please set numClusters to -1 | ||
| numClusters: 4, | ||
|
|
||
| // If numClusters is not -1, then threshold is ignored. | ||
| // | ||
| // A larger threshold leads to fewer clusters, i.e., fewer speakers | ||
| // A smaller threshold leads to more clusters, i.e., more speakers | ||
| // You need to tune it by yourself. | ||
| threshold: 0.5, | ||
| }, | ||
|
|
||
| // If a segment is shorter than minDurationOn, we discard it | ||
| minDurationOn: 0.2, // in seconds | ||
|
|
||
| // If the gap between two segments is less than minDurationOff, then we | ||
| // merge these two segments into a single one | ||
| minDurationOff: 0.5, // in seconds | ||
| }; | ||
|
|
||
| const waveFilename = './0-four-speakers-zh.wav'; | ||
|
|
||
| const sd = new sherpa_onnx.OfflineSpeakerDiarization(config); | ||
| console.log('Started') | ||
|
|
||
| const wave = sherpa_onnx.readWave(waveFilename); | ||
| if (sd.sampleRate != wave.sampleRate) { | ||
| throw new Error( | ||
| `Expected sample rate: ${sd.sampleRate}, given: ${wave.sampleRate}`); | ||
| } | ||
|
|
||
| const segments = sd.process(wave.samples); | ||
| console.log(segments); |
This file contains 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
32 changes: 32 additions & 0 deletions
32
scripts/node-addon-api/lib/non-streaming-speaker-diarization.js
This file contains 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 +1,32 @@ | ||
| const addon = require('./addon.js'); | ||
|
|
||
| class OfflineSpeakerDiarization { | ||
| constructor(config) { | ||
| this.handle = addon.createOfflineSpeakerDiarization(config); | ||
| this.config = config; | ||
|
|
||
| this.sampleRate = addon.getOfflineSpeakerDiarizationSampleRate(this.handle); | ||
| } | ||
|
|
||
| /** | ||
| * samples is a 1-d float32 array. Each element of the array should be | ||
| * in the range [-1, 1]. | ||
| * | ||
| * We assume its sample rate equals to this.sampleRate. | ||
| * | ||
| * Returns an array of object, where an object is | ||
| * | ||
| * { | ||
| * "start": start_time_in_seconds, | ||
| * "end": end_time_in_seconds, | ||
| * "speaker": an_integer, | ||
| * } | ||
| */ | ||
| process(samples) { | ||
| return addon.offlineSpeakerDiarizationProcess(this.handle, samples); | ||
| } | ||
| } | ||
|
|
||
| module.exports = { | ||
| OfflineSpeakerDiarization, | ||
| } |
This file contains 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 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
Oops, something went wrong.