a-froghyar

Hey @krisgesling, thanks for your reply. I'm trying to get the app up and running locally and start debugging (thinkin about adding a feature), however I have a hard time...

@arif334 I've had this issue before and what I would suggest is increasing `min_audio_len`. I had NaN issues in the posterior as well before when too short samples were fed...

are you using phonemes? `use_phonemes` is False in your config

I'd also try to reduce `max_audio_len` to 6 seconds

@lucashueda Capacitron VAE: https://github.com/coqui-ai/TTS/pull/510

I'm experiencing the same thing, any news on this?

I've actually found that if you revert to the one checkpoint before you got stuck and the loss exploded every time you re-run training, the old checkpoint will continue without...

@sungjae-cho @Tomiinek I have experimented with Aeneas before with very long audio data and I've realised that alignment works almost 100% if the audio is max. 60 minutes. I actually...

Hey, could anyone share a recipe for increasing the sample rate?

Hey @alokprasad I meant regarding the training and synthesis within the repo - I'd like to train Tacotron-2 and LPCNet with 24kHz samples.