Instructions to use efficient-nlp/stt-1b-en_fr-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use efficient-nlp/stt-1b-en_fr-quantized with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "efficient-nlp/stt-1b-en_fr-quantized" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("efficient-nlp/stt-1b-en_fr-quantized") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2aeba9f157a6576f0370561aa4bd001af60391944e4a16d63dfbfc08600762df
- Size of remote file:
- 120 kB
- SHA256:
- cd87dd5d17169151782ac700280ec057e5d658a9afbe238a048ea5ff318cce69
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.