ecker
-
https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.
XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG
- Joined on
2022-10-10
Block a user
Generated voices from training data always garbled.... but works fine using tortoise-tts-fast ... (?)
I figured I'll (ashamedly) mention it here, since this issues thread was the reason why I removed it in the first place: I added WhisperX back. It won't install by default to avoid any more…
a6daf289bc
when the sanitizer thingy works in testing but it doesn't outside of testing, and you have to retranscribe for the fourth time today
0ea93a7f40
more cleanup, use 24KHz for preparing for VALL-E (encodec will resample to 24Khz anyways, makes audio a little nicer), some other things
Can't train a single good model
...because you need to click (Re)compute Voice Latents when you want to regenerate them.
I don't have ways to regenerate latents automatically when there's a change in chunk size, hence the…
d2a9ab9e41
remove redundant phonemize for vall-e (oops), quantize all files and then phonemize all files for cope optimization, load alignment model once instead of for every transcription (speedup with whisperx)
932eaccdf5
added whisper transcription 'sanitizing' (collapse very short transcriptions to the previous segment) (I really have to stop having several copies spanning several machines for AIVC, I keep reverting shit)
736cdc8926
disable diarization for whisperx as it's just a useless performance hit (I don't have anything that's multispeaker within the same audio file at the moment)
4056a27bcb
begrudgingly added back whisperx integration (VAD/Diarization testing, I really, really need accurate timestamps before dumping mondo amounts of time on training a dataset)
"No such file or directory: 'train.sh'" after updating to f822c87344d2ce01bd077b48d9db42740c51ea04