Instructions to use gatilin/lfm3-omni-liquidcodec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gatilin/lfm3-omni-liquidcodec with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("gatilin/lfm3-omni-liquidcodec", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download validation.json from gatilin/lfm3-omni-liquidcodec: direct link, hf CLI and curl.
- Browser
- Download file 378 Bytes
-
https://huggingface.co/gatilin/lfm3-omni-liquidcodec/resolve/main/validation.json
- Command line
-
hf download hf://gatilin/lfm3-omni-liquidcodec/validation.json
-
curl -L -o validation.json https://huggingface.co/gatilin/lfm3-omni-liquidcodec/resolve/main/validation.json
378 Bytes
| { | |
| "strict_load": true, | |
| "input": "synthetic 440 Hz sine wave, 24 kHz, 4800 samples", | |
| "device": "cpu", | |
| "codes_shape": [ | |
| 1, | |
| 12, | |
| 3 | |
| ], | |
| "output_shape": [ | |
| 1, | |
| 4800 | |
| ], | |
| "finite": true, | |
| "repeat_max_abs_error": 0.0, | |
| "elapsed_seconds": 23.12, | |
| "limitations": "Synthetic signal smoke test only; no source-model parity or speech quality evaluation." | |
| } | |