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

Upload speaker embedding models to huggingface (#1428)

Browse Source 
See also
https://huggingface.co/spaces/k2-fsa/speaker-diarization
This commit is contained in:
Fangjun Kuang
2024-10-14 16:20:00 +08:00
committed by GitHub
parent 99f320b893
commit df4150dc5d
6 changed files with 95 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/3dspeaker/run.sh
View File

@@ -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
}

9
scripts/nemo/speaker-verification/run.sh
View File

@@ -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