Instructions to use AdoCleanCode/LAVCO-codec-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdoCleanCode/LAVCO-codec-v2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AdoCleanCode/LAVCO-codec-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download llasa_vc_config.json from AdoCleanCode/LAVCO-codec-v2: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/AdoCleanCode/LAVCO-codec-v2/resolve/085f47ff4bbdbcd5c92627da8f08c1935eaeb613/llasa_vc_config.json
- Command line
-
hf download hf://AdoCleanCode/LAVCO-codec-v2@085f47ff4bbdbcd5c92627da8f08c1935eaeb613/llasa_vc_config.json
-
curl -L -o llasa_vc_config.json https://huggingface.co/AdoCleanCode/LAVCO-codec-v2/resolve/085f47ff4bbdbcd5c92627da8f08c1935eaeb613/llasa_vc_config.json
256 Bytes
| { | |
| "hidden_size": 2048, | |
| "u_start_id": 128262, | |
| "u_end_id": 128263, | |
| "g_start_id": 128260, | |
| "g_end_id": 128261, | |
| "pad_id": 128009, | |
| "instruction_prefix": "Convert ", | |
| "instruction_middle": " into speech using this speaker: ", | |
| "codec_only": true | |
| } |