Feature Extraction
MLX
resnet34_embedding
speaker-recognition
speaker-embedding
speaker-diarization
audio
resnet
apple-silicon
Instructions to use mlx-community/wespeaker-voxceleb-resnet34-LM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/wespeaker-voxceleb-resnet34-LM with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir wespeaker-voxceleb-resnet34-LM mlx-community/wespeaker-voxceleb-resnet34-LM
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
MLX-Audio integration
#1
by prince-canuma - opened
Hey @BMP
This is an awesome port and I believe it would be a great addition to mlx-audio.
We already support much of the audio tasks, and speaker embedding similarity would be a great addition!
Hey @prince-canuma !!
Thanks for your comment.
What a great job with mlx-audio!!!, very happy to share with the community.
Here's its the pubic repository of the port: https://github.com/billymolina/speaker-diarization-community-1-mlx