Vedi su GitHub
 (1 commento) (0 reazioni) (0 assegnatari)Python (2849 fork)batch import
bughelp wanted

Metriche repository

Star
 (18.427 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

I am training with COLAB, but the voice of the model trained yesterday and today seems noisier and blurred compared to the voice of the previously trained model. It feels like the pre-trained models are not working. The former is the model learned previously and the latter is the model learned today. https://www.axfc.net/u/4065483 Although trained on the same data set, the sound is clearly degraded in the latter. https://www.axfc.net/u/4065492 I tried learning at 40k and it was clear. I tried learning at 48k and it seemed to cause problems.

Guida contributor