Instructions to use AXERA-TECH/CosyVoice2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/CosyVoice2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="AXERA-TECH/CosyVoice2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/CosyVoice2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download token2wav-axmodels/flow_encoder_53.axmodel from AXERA-TECH/CosyVoice2: direct link, hf CLI and curl.
- Browser
- Download file 42.5 MB
-
https://huggingface.co/AXERA-TECH/CosyVoice2/resolve/main/token2wav-axmodels/flow_encoder_53.axmodel
- Command line
-
hf download hf://AXERA-TECH/CosyVoice2/token2wav-axmodels/flow_encoder_53.axmodel
-
curl -L -o flow_encoder_53.axmodel https://huggingface.co/AXERA-TECH/CosyVoice2/resolve/main/token2wav-axmodels/flow_encoder_53.axmodel
42.5 MB
- Xet hash:
- c4430dd58a4ec81317cfb9594d323af4c1b9c24d2e535f48dedcdf4645ff8179
- Size of remote file:
- 42.5 MB
- SHA256:
- b7eea4e2b6cbc3cf6b4a8b0630114bee99b158debdc9037d807bd2d82f458c87
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.