✨ Supervoice Flow

Feel free to join my Discord Server to discuss this model!

Description

A foundational model for voice audio, could be effectively fine-tuned on a single GPU to implement text-to-speech, text enchancement and diarization. Based on original Speechflow Paper: Generative Pre-training for Speech with Flow Matching

Examples of finetunes

• Supervoice Enhance - cleanup of background noise

Licence

MIT