xuning / sherpaonnx

转到一个项目
Toggle navigation Toggle navigation pinning
Fangjun Kuang
Committed by GitHub
df4150dc 1 parent 99f320b8

Upload speaker embedding models to huggingface (#1428) 

See also
https://huggingface.co/spaces/k2-fsa/speaker-diarization
内嵌 并排对比
正在显示 6 个修改的文件 包含 88 行增加 和 8 行删除
... ... @@ -15,7 +15,7 @@ jobs:
strategy:
fail-fast: false
matrix:
os: [macos-latest]
os: [ubuntu-latest]
python-version: ["3.8"]
steps:
... ... @@ -43,3 +43,28 @@ jobs:
repo_name: k2-fsa/sherpa-onnx
repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
tag: speaker-recongition-models
- name: Publish to huggingface
env:
HF_TOKEN: ${{ secrets.HF_TOKEN }}
uses: nick-fields/retry@v3
with:
max_attempts: 20
timeout_seconds: 200
shell: bash
command: |
git config --global user.email "csukuangfj@gmail.com"
git config --global user.name "Fangjun Kuang"
d=speaker-embedding-models
export GIT_LFS_SKIP_SMUDGE=1
export GIT_CLONE_PROTECTION_ACTIVE=false
git clone https://huggingface.co/csukuangfj/$d huggingface
mv -v ./*.onnx ./huggingface
cd huggingface
git lfs track "*.onnx"
git status
git add .
git status
git commit -m "add models"
git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main
... ...
... ... @@ -15,7 +15,7 @@ jobs:
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest]
os: [macos-latest]
python-version: ["3.10"]
steps:
... ... @@ -43,3 +43,28 @@ jobs:
repo_name: k2-fsa/sherpa-onnx
repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
tag: speaker-recongition-models
- name: Publish to huggingface
env:
HF_TOKEN: ${{ secrets.HF_TOKEN }}
uses: nick-fields/retry@v3
with:
max_attempts: 20
timeout_seconds: 200
shell: bash
command: |
git config --global user.email "csukuangfj@gmail.com"
git config --global user.name "Fangjun Kuang"
d=speaker-embedding-models
export GIT_LFS_SKIP_SMUDGE=1
export GIT_CLONE_PROTECTION_ACTIVE=false
git clone https://huggingface.co/csukuangfj/$d huggingface
mv -v ./*.onnx ./huggingface
cd huggingface
git lfs track "*.onnx"
git status
git add .
git status
git commit -m "add models"
git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main
... ...
... ... @@ -48,3 +48,28 @@ jobs:
repo_name: k2-fsa/sherpa-onnx
repo_token: ${{ secrets.UPLOAD_GH_SHERPA_ONNX_TOKEN }}
tag: speaker-recongition-models
- name: Publish to huggingface
env:
HF_TOKEN: ${{ secrets.HF_TOKEN }}
uses: nick-fields/retry@v3
with:
max_attempts: 20
timeout_seconds: 200
shell: bash
command: |
git config --global user.email "csukuangfj@gmail.com"
git config --global user.name "Fangjun Kuang"
d=speaker-embedding-models
export GIT_LFS_SKIP_SMUDGE=1
export GIT_CLONE_PROTECTION_ACTIVE=false
git clone https://huggingface.co/csukuangfj/$d huggingface
mv -v ./*.onnx ./huggingface
cd huggingface
git lfs track "*.onnx"
git status
git add .
git status
git commit -m "add models"
git push https://csukuangfj:$HF_TOKEN@huggingface.co/csukuangfj/$d main
... ...
... ... @@ -89,7 +89,8 @@ with the following APIs
installing anything. All you need is a browser.</summary>
| Description | URL |
|-------------------------------------------------------|------------------------------------|
|-------------------------------------------------------|-----------------------------------------|
| Speaker diarization | [Click me][hf-space-speaker-diarization]|
| Speech recognition | [Click me][hf-space-asr] |
| Speech recognition with [Whisper][Whisper] | [Click me][hf-space-asr-whisper] |
| Speech synthesis | [Click me][hf-space-tts] |
... ... @@ -240,6 +241,7 @@ Video demo in Chinese: [爆了！炫神教你开打字挂！真正影响胜率
[VisionFive 2]: https://www.starfivetech.com/en/site/boards
[旭日X3派]: https://developer.horizon.ai/api/v1/fileData/documents_pi/index.html
[爱芯派]: https://wiki.sipeed.com/hardware/zh/maixIII/ax-pi/axpi.html
[hf-space-speaker-diarization]: https://huggingface.co/spaces/k2-fsa/speaker-diarization
[hf-space-asr]: https://huggingface.co/spaces/k2-fsa/automatic-speech-recognition
[Whisper]: https://github.com/openai/whisper
[hf-space-asr-whisper]: https://huggingface.co/spaces/k2-fsa/automatic-speech-recognition-with-whisper
... ...
... ... @@ -4,10 +4,10 @@ set -e
function install_3d_speaker() {
echo "Install 3D-Speaker"
git clone https://github.com/alibaba-damo-academy/3D-Speaker.git
git clone https://github.com/modelscope/3D-Speaker
pushd 3D-Speaker
pip install -q -r ./requirements.txt
pip install -q modelscope onnx onnxruntime kaldi-native-fbank
pip install -q modelscope==1.14.0 onnx onnxruntime kaldi-native-fbank
popd
}
... ...
... ... @@ -7,14 +7,17 @@ function install_nemo() {
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
python3 get-pip.py
pip install torch==2.1.0+cpu torchaudio==2.1.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
pip install torch==2.1.0 torchaudio==2.1.0 -f https://download.pytorch.org/whl/torch_stable.html
pip install wget text-unidecode matplotlib>=3.3.2 onnx onnxruntime pybind11 Cython einops kaldi-native-fbank soundfile
pip install -qq wget text-unidecode matplotlib>=3.3.2 onnx onnxruntime pybind11 Cython einops kaldi-native-fbank soundfile
pip install -qq ipython
sudo apt-get install -q -y sox libsndfile1 ffmpeg python3-pip
# sudo apt-get install -q -y sox libsndfile1 ffmpeg python3-pip ipython
BRANCH='main'
python3 -m pip install git+https://github.com/NVIDIA/NeMo.git@$BRANCH#egg=nemo_toolkit[asr]
pip install numpy==1.26.4
}
install_nemo
... ...