Text-to-Speech
Transformers
Safetensors
omnivoice
tts
singing
emotion
expressive-tts
multilingual
voice-cloning
Instructions to use ModelsLab/omnivoice-singing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelsLab/omnivoice-singing with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="ModelsLab/omnivoice-singing")# pip install -U transformers accelerate # Load model directly from transformers import OmniVoice model = OmniVoice.from_pretrained("ModelsLab/omnivoice-singing", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download audio_tokenizer/preprocessor_config.json from ModelsLab/omnivoice-singing: direct link, hf CLI and curl.
- Browser
- Download file 206 Bytes
-
https://huggingface.co/ModelsLab/omnivoice-singing/resolve/main/audio_tokenizer/preprocessor_config.json
- Command line
-
hf download hf://ModelsLab/omnivoice-singing/audio_tokenizer/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/ModelsLab/omnivoice-singing/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 | |
| } | |