Audio Classification
speechbrain
PyTorch
English
embeddings
Speaker
Verification
Identification
xvectors
TDNN
Instructions to use speechbrain/spkrec-xvect-voxceleb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use speechbrain/spkrec-xvect-voxceleb with speechbrain:
from speechbrain.pretrained import EncoderClassifier model = EncoderClassifier.from_hparams( "speechbrain/spkrec-xvect-voxceleb" ) model.classify_file("file.wav") - Notebooks
- Google Colab
- Kaggle
How can I use this with the transformers library?
#1
by MrEnigma - opened
Speechbrain library doesn't seem to work in Windows.
all you need is relevant files to download (for now I am going to download all files) then pass the location (download location) as argument instead of "speechbrain/spkrec-xvect-voxceleb" in source in the line: EncoderClassifier.from_hparams(source="speechbrain/spkrec-xvect-voxceleb", savedir="pretrained_models/spkrec-xvect-voxceleb")
also, don't use savedir when you are doing it manualy in windows, do this instead:
EncoderClassifier.from_hparams(source="download_directory_where_model_files_are")