search

KdaiP / StableTTS

Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
MIT License
348 stars 39 forks source link

the timbre for zero-shot seems to be not good #14

Open zhazhuanling12 opened 5 months ago

zhazhuanling12 commented 5 months ago

concat.zip I don't know whether it supports zero-shot

KdaiP commented 3 weeks ago

Thank you for your feedback! You can try the latest version, which should improve the timbre for zero-shot to some extent. However, due to the limited model parameters and dataset size, we still recommend fine-tuning or training for better results.