Fish Agent V0.1 3B is a groundbreaking Voice-to-Voice model capable of capturing and generating environmental audio information with unprecedented accuracy. What sets it apart is its semantic-token-free architecture, eliminating the need for traditional semantic encoders/decoders like Whisper and CosyVoice.

Additionally, it stands as a state-of-the-art text-to-speech (TTS) model, trained on an extensive dataset of 700,000 hours of multilingual audio content.

This model is a continue-pretrained version of Qwen-2.5-3B-Instruct for 200B voice & text tokens.

The model supports the following languages with their respective training data sizes:

For detailed information and implementation guidelines, please visit our Fish Speech GitHub repository.

If you find this repository helpful in your work, please consider citing:

This model and its associated code are released under the BY-CC-NC-SA-4.0 license, allowing for non-commercial use with appropriate attribution.