-
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
1a0dd2cd77
fixed phonemizer, added calculating total duration (and duration by speaker), updated default symmap, some other things maybe
Should be fixed in the latest commit.
f025470d60
Merge pull request 'Update tortoise/utils/devices.py vram issue' (#44) from aJoe/tortoise-tts:main into main
815ae5d707
Merge pull request 'feat: support .flac voice files' (#43) from NtTestAlert/tortoise-tts:support_flac_voice into main
f025470d60
Merge pull request 'Update tortoise/utils/devices.py vram issue' (#44) from aJoe/tortoise-tts:main into main
segment and transcribe for data prep as well as to generate YAML configuration for training.
They're within the web UI tabs.
I'm a bit fried so bear with me if I'm incoherent.
The lifeiteng implementation leverages Lhotse + k2 + icefall to prepare its dataset. I can't quite recall the pros and cons I've gleaned with…
348c6e73a1
reduce batch size if OOM during forward pass (tries up to 4 times before triggering hard OOM), also a VRAM reduction from naive ZeRO settings that sometimes triggered OOM during backwards pass from allocating 512MiB
Are we still at this stage?
mmm
It's hard to say still. I think my new-er understanding of how the implementation works, and how VALL-E itself works, wants to say it should be pretty…
Anywho, I'm blasting ropes from how training is shaping up now. It was a really rocky start, but it seems to be smooth sailing now, as I'm getting actual clean real output now from utilizing…
Yeah the one on the doc are the golden version! At least according to the anon who ripped them (I didn't check it myself)...
Yeah, they're from Golden. I tried adding in the Chie lines the…