Open avramandrei opened 1 year ago
Hi, @avramandrei
Thanks for your attention to SpeechT5. The fine-tuned SpeechT5 model on tasks SE task were not provided online.
If you want to reimplement the recipe of the SE task, the scripts of the VC tasks can be helpful because both tasks have similar modeling manner and training manifest. Using the SE data can produce SE-funetuned SpeechT5 model.
Thanks.
Did anyone try to create a model? Does using VC transformers model without passing voice latents parameter works for training?
Hi,
Could you tell me where I can find the fine-tuned SpeechT5 for the speech enhancement task? Also, a link to how I can load and use it would be very useful.
Thank you, Andrei