mimi-voice-ft-adapter

Fused Mimi + MLP adapter checkpoint used as the default adapter for mimi-voice-ft inference.

Files

• voice_adapter_20250810_101444_fused.pth

Training

• Trained against kyutai/tts-voices
• Intended for prompt creation with the mimi-voice-ft workflow
• Consumed together with Kyutai TTS models such as kyutai/tts-1.6b-en_fr

License and Usage

This model is released under the Creative Commons Attribution-NonCommercial 4.0 International license (CC BY-NC 4.0). Because the training data is not MIT-licensed, this checkpoint should not be treated as MIT or used under MIT terms.

Summary:

• You may use, share, and adapt the model for non-commercial, research, and educational purposes.
• You must provide proper attribution to the original author and this model repo.
• You may not use this model or derivatives for commercial purposes.
• You may not use this model to impersonate or clone real individuals without their explicit consent.

Attribution

If you use or modify this model, acknowledge shaans/mimi-voice-ft-adapter or provide equivalent attribution.

Full License

https://creativecommons.org/licenses/by-nc/4.0

By downloading or using this model, you agree to these terms.