-
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
Incidentally, I've found that TensorBoard has caused a similar issue causing this VALL-E implementation to segfault as well, although the…
ee1b048d07
when creating the train/validatio datasets, use segments if the main audio's duration is too long, and slice to make the segments if they don't exist
but I get a ffmpeg failure on generate transcript (ffmpeg.exe is in ./bin) not sure if they are related?
You'll need to uninstall and install ffmpeg-python, for some reason.
Windows:
…You can disable the Delete Non-Final Outputs setting under Settings to retain the individual pieces that get combined.
050bcefd73
resample to 22.5K when creating training inputs (to avoid redundant downsampling when loaded for training, even though most of my inputs are already at 22.5K), generalized resampler function to cache and reuse them, do not unload whisper when done transcribing since it gets unloaded anyways for any other non-transcription task
239c984850
move validating audio to creating the text files instead, consider audio longer than 11 seconds invalid, consider text lengths over 200 invalid
Figured it out. In the future, you should really validate your generation settings.
Your candidate size is set to 0. Set it to 1.