Instructions to use tiny-random/omnivoice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiny-random/omnivoice with Transformers:
# Load model directly from transformers import OmniVoice model = OmniVoice.from_pretrained("tiny-random/omnivoice", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download audio_tokenizer/preprocessor_config.json from tiny-random/omnivoice: direct link, hf CLI and curl.
- Browser
- Download file 206 Bytes
-
https://huggingface.co/tiny-random/omnivoice/resolve/main/audio_tokenizer/preprocessor_config.json
- Command line
-
hf download hf://tiny-random/omnivoice/audio_tokenizer/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/tiny-random/omnivoice/resolve/main/audio_tokenizer/preprocessor_config.json
206 Bytes
| { | |
| "feature_extractor_type": "DacFeatureExtractor", | |
| "feature_size": 1, | |
| "hop_length": 960, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000 | |
| } | |