-
Notifications
You must be signed in to change notification settings - Fork 477
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Browse files
Browse the repository at this point in the history
- Loading branch information
1 parent
471cbd8
commit 620597f
Showing
9 changed files
with
276 additions
and
12 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| name: export-revai-segmentation-to-onnx | ||
|
|
||
| on: | ||
| workflow_dispatch: | ||
|
|
||
| concurrency: | ||
| group: export-revai-segmentation-to-onnx-${{ github.ref }} | ||
| cancel-in-progress: true | ||
|
|
||
| jobs: | ||
| export-revai-segmentation-to-onnx: | ||
| if: github.repository_owner == 'k2-fsa' || github.repository_owner == 'csukuangfj' | ||
| name: export revai segmentation models to ONNX | ||
| runs-on: ${{ matrix.os }} | ||
| strategy: | ||
| fail-fast: false | ||
| matrix: | ||
| os: [macos-latest] | ||
| python-version: ["3.10"] | ||
|
|
||
| steps: | ||
| - uses: actions/checkout@v4 | ||
|
|
||
| - name: Setup Python ${{ matrix.python-version }} | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: ${{ matrix.python-version }} | ||
|
|
||
| - name: Install pyannote | ||
| shell: bash | ||
| run: | | ||
| pip install pyannote.audio onnx==1.15.0 onnxruntime==1.16.3 | ||
| - name: Run | ||
| shell: bash | ||
| run: | | ||
| d=sherpa-onnx-reverb-diarization-v1 | ||
| src=$PWD/$d | ||
| mkdir -p $src | ||
| pushd scripts/pyannote/segmentation | ||
| ./run-revai.sh | ||
| cp ./*.onnx $src/ | ||
| cp ./README.md $src/ | ||
| cp ./LICENSE $src/ | ||
| cp ./run-revai.sh $src/run.sh | ||
| cp ./*.py $src/ | ||
| popd | ||
| ls -lh $d | ||
| tar cjfv $d.tar.bz2 $d | ||
| - name: Release | ||
| uses: svenstaro/upload-release-action@v2 | ||
| with: | ||
| file_glob: true | ||
| file: ./*.tar.bz2 | ||
| overwrite: true | ||
| repo_name: k2-fsa/sherpa-onnx | ||
| repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }} | ||
| tag: speaker-segmentation-models | ||
|
|
||
| - name: Publish to huggingface | ||
| env: | ||
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | ||
| uses: nick-fields/retry@v3 | ||
| with: | ||
| max_attempts: 20 | ||
| timeout_seconds: 200 | ||
| shell: bash | ||
| command: | | ||
| git config --global user.email "[email protected]" | ||
| git config --global user.name "Fangjun Kuang" | ||
| d=sherpa-onnx-reverb-diarization-v1 | ||
| export GIT_LFS_SKIP_SMUDGE=1 | ||
| export GIT_CLONE_PROTECTION_ACTIVE=false | ||
| git clone https://huggingface.co/csukuangfj/$d huggingface | ||
| cp -v $d/* ./huggingface | ||
| cd huggingface | ||
| git lfs track "*.onnx" | ||
| git status | ||
| git add . | ||
| git status | ||
| git commit -m "add models" | ||
| git push https://csukuangfj:[email protected]/csukuangfj/$d main |
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 +1,89 @@ | ||
| #!/usr/bin/env python3 | ||
|
|
||
| import argparse | ||
| from dataclasses import dataclass | ||
| from typing import List | ||
|
|
||
| import jinja2 | ||
|
|
||
|
|
||
| def get_args(): | ||
| parser = argparse.ArgumentParser() | ||
| parser.add_argument( | ||
| "--total", | ||
| type=int, | ||
| default=1, | ||
| help="Number of runners", | ||
| ) | ||
| parser.add_argument( | ||
| "--index", | ||
| type=int, | ||
| default=0, | ||
| help="Index of the current runner", | ||
| ) | ||
| return parser.parse_args() | ||
|
|
||
|
|
||
| @dataclass | ||
| class SpeakerSegmentationModel: | ||
| model_name: str | ||
| short_name: str = "" | ||
|
|
||
|
|
||
| def get_models() -> List[SpeakerSegmentationModel]: | ||
| models = [ | ||
| SpeakerSegmentationModel( | ||
| model_name="sherpa-onnx-pyannote-segmentation-3-0", | ||
| short_name="pyannote_audio", | ||
| ), | ||
| SpeakerSegmentationModel( | ||
| model_name="sherpa-onnx-reverb-diarization-v1", | ||
| short_name="revai_v1", | ||
| ), | ||
| ] | ||
|
|
||
| return models | ||
|
|
||
|
|
||
| def main(): | ||
| args = get_args() | ||
| index = args.index | ||
| total = args.total | ||
| assert 0 <= index < total, (index, total) | ||
|
|
||
| all_model_list = get_models() | ||
|
|
||
| num_models = len(all_model_list) | ||
|
|
||
| num_per_runner = num_models // total | ||
| if num_per_runner <= 0: | ||
| raise ValueError(f"num_models: {num_models}, num_runners: {total}") | ||
|
|
||
| start = index * num_per_runner | ||
| end = start + num_per_runner | ||
|
|
||
| remaining = num_models - args.total * num_per_runner | ||
|
|
||
| print(f"{index}/{total}: {start}-{end}/{num_models}") | ||
|
|
||
| d = dict() | ||
| d["model_list"] = all_model_list[start:end] | ||
| if index < remaining: | ||
| s = args.total * num_per_runner + index | ||
| d["model_list"].append(all_model_list[s]) | ||
| print(f"{s}/{num_models}") | ||
|
|
||
| filename_list = ["./build-apk-speaker-diarization.sh"] | ||
| for filename in filename_list: | ||
| environment = jinja2.Environment() | ||
| with open(f"{filename}.in") as f: | ||
| s = f.read() | ||
| template = environment.from_string(s) | ||
|
|
||
| s = template.render(**d) | ||
| with open(filename, "w") as f: | ||
| print(s, file=f) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| main() |
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 +1,48 @@ | ||
| #!/usr/bin/env bash | ||
| # Copyright 2024 Xiaomi Corp. (authors: Fangjun Kuang) | ||
|
|
||
| export SHERPA_ONNX_IS_REVAI=1 | ||
|
|
||
| set -ex | ||
| function install_pyannote() { | ||
| pip install pyannote.audio onnx onnxruntime | ||
| } | ||
|
|
||
| function download_test_files() { | ||
| curl -SL -O https://huggingface.co/Revai/reverb-diarization-v1/resolve/main/pytorch_model.bin | ||
| curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/lei-jun-test.wav | ||
| } | ||
|
|
||
| install_pyannote | ||
| download_test_files | ||
|
|
||
| ./export-onnx.py | ||
| ./preprocess.sh | ||
|
|
||
| echo "----------torch----------" | ||
| ./vad-torch.py | ||
|
|
||
| echo "----------onnx model.onnx----------" | ||
| ./vad-onnx.py --model ./model.onnx --wav ./lei-jun-test.wav | ||
|
|
||
| echo "----------onnx model.int8.onnx----------" | ||
| ./vad-onnx.py --model ./model.int8.onnx --wav ./lei-jun-test.wav | ||
|
|
||
| curl -SL -O https://huggingface.co/Revai/reverb-diarization-v1/resolve/main/LICENSE | ||
|
|
||
| cat >README.md << EOF | ||
| # Introduction | ||
| Models in this file are converted from | ||
| https://huggingface.co/Revai/reverb-diarization-v1/tree/main | ||
| Note that it is accessible under a non-commercial license. | ||
| Please see ./LICENSE for details. | ||
| See also | ||
| https://www.rev.com/blog/speech-to-text-technology/introducing-reverb-open-source-asr-diarization | ||
| EOF | ||
|
|
||
|
|
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 |
|---|---|---|
| @@ -1,4 +1,5 @@ | ||
| #!/usr/bin/env python3 | ||
| # Copyright 2024 Xiaomi Corp. (authors: Fangjun Kuang) | ||
|
|
||
| """ | ||
| Please refer to | ||
|
|
||
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