deepglugs

I'm training my own model with 0.5hrs of data (on top of a pre-trained model). The samples seem to often cut out early before the utterance is complete. Is this...

incompatibility with pytorch >= 1.7.0

2

Upgraded to 1.9.0 and flowtron inference stopped producing anything but noise. After downgrading to pytorch 1.6.0, it started working again. Anyone else seeing this?

Should there be any noise output?

6

I'm having trouble getting any decent results out of flowtron and trying to figure out why. With my somewhat small dataset (0.67hrs) and warmstart from ljs, I can't seem to...

Save/Load individual unets to different files

1

It would be interesting to train unet1 and save to one file and simultaneously train unet2 on another GPU and save to a different file. These would need to be...

sync_batchnorm missing

2

Looks like this file might be missing from source: ```ModuleNotFoundError: No module named 'models.networks.sync_batchnorm' ```

Trainer support for audio file, prompt pairs

2

Most of my data is split in file.wav and file.txt or in json files with "path/to/file.wav": "the transcription of the audio" mappings. It looks like Trainer only supports audio files....