Instructions to use fishaudio/fish-speech-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fishaudio/fish-speech-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="fishaudio/fish-speech-1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fishaudio/fish-speech-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download vits_decoder_v1.1.ckpt from fishaudio/fish-speech-1: direct link, hf CLI and curl.
- Browser
- Download file 863 MB
-
https://huggingface.co/fishaudio/fish-speech-1/resolve/main/vits_decoder_v1.1.ckpt
- Command line
-
hf download hf://fishaudio/fish-speech-1/vits_decoder_v1.1.ckpt
-
curl -L -o vits_decoder_v1.1.ckpt https://huggingface.co/fishaudio/fish-speech-1/resolve/main/vits_decoder_v1.1.ckpt
863 MB
- Xet hash:
- a397577909e5cd37526b1739e3fd6fb38765210955bfb2122254735fbd2bf28e
- Size of remote file:
- 863 MB
- SHA256:
- 8ccd1745db022f8878c4a8323499ffdc665c282ecbc7adb16eb0802397f954e4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.