Instructions to use timofeiiz/soundstream-impl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timofeiiz/soundstream-impl with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timofeiiz/soundstream-impl", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from timofeiiz/soundstream-impl: direct link, hf CLI and curl.
- Browser
- Download file 236 Bytes
-
https://huggingface.co/timofeiiz/soundstream-impl/resolve/main/config.json
- Command line
-
hf download hf://timofeiiz/soundstream-impl/config.json
-
curl -L -o config.json https://huggingface.co/timofeiiz/soundstream-impl/resolve/main/config.json
236 Bytes
| { | |
| "model_type": "soundstream", | |
| "channels": 32, | |
| "latent_dim": 512, | |
| "codebook_size": 1024, | |
| "num_quantizers": 8, | |
| "auto_map": { | |
| "AutoConfig": "config_model.SoundStreamConfig", | |
| "AutoModel": "model.SoundStreamCodec" | |
| } | |
| } | |