fish-speech-1.4

Fish Speech V1.4

This is a re-upload of Fish Audio's Fish Speech 1.4 weights, with some minor changes:

• Weights exported to .safetensors from .pth
• Weight normalization removed from HiFiGAN weights to increase inference speeds
• firefly_gan_vq.yaml config added from original repo

All credit to the original authors; sharing under original non-commercial license.

Original README below

Fish Speech V1.4 is a leading text-to-speech (TTS) model trained on 700k hours of audio data in multiple languages.

Supported languages:

• English (en) ~300k hours
• Chinese (zh) ~300k hours
• German (de) ~20k hours
• Japanese (ja) ~20k hours
• French (fr) ~20k hours
• Spanish (es) ~20k hours
• Korean (ko) ~20k hours
• Arabic (ar) ~20k hours

Please refer to Fish Speech Github for more info.
Demo available at Fish Audio.

Citation

If you found this repository useful, please consider citing this work:

@misc{fish-speech-v1.4,
  author = {Shijia Liao, Tianyu Li, etc},
  title = {Fish Speech V1.4},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/fishaudio/fish-speech}}
}

License

This model is permissively licensed under the BY-CC-NC-SA-4.0 license. The source code is released under BSD-3-Clause license.