mrq
16 Followers · 0 Following

  • 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 Oct 10, 2022
Repositories
18
 Projects Packages Public Activity Starred Repositories
Loading Heatmap…

mrq deleted branch main from mrq/bitsandbytes-rocm

2023-10-13 00:16:42 +07:00

mrq pushed to master at mrq/bitsandbytes-rocm

2023-10-13 00:16:29 +07:00

mrq created branch master in mrq/bitsandbytes-rocm

2023-10-13 00:16:27 +07:00

mrq deleted branch master from mrq/bitsandbytes-rocm

2023-10-13 00:16:16 +07:00

mrq created branch stale in mrq/bitsandbytes-rocm

2023-10-13 00:16:16 +07:00

mrq pushed to main at mrq/bitsandbytes-rocm

2023-10-13 00:15:27 +07:00

mrq created branch main in mrq/bitsandbytes-rocm

2023-10-13 00:15:25 +07:00

mrq commented on issue mrq/ai-voice-cloning#411

Cant get training to work? (windows 10 nvida GPU)

Well, from a glance your training settings are whack. Your dataset size is 93, yet your batch size is set to that (which is already an uneven number). Your gradient accumulation factor is also…

2023-10-12 15:15:26 +07:00

mrq commented on issue mrq/ai-voice-cloning#410

Learning state restart question

> the learning rate will restart only 4 times in the entire training Correct.

2023-10-12 13:14:12 +07:00

mrq pushed to master at mrq/vall-e

  • 08bae355eb actually use langs from the dataloader

2023-10-12 02:23:20 +07:00

mrq pushed to master at mrq/vall-e

  • 8193d6b938 actually use langs from the dataloader

2023-10-12 02:16:37 +07:00

mrq pushed to master at mrq/vall-e

2023-10-12 01:49:03 +07:00

mrq pushed to master at mrq/vall-e

  • 8740cdefc6 added initial support for languages (still testing, marked as model version 3), added experimental 'context extend by limiting the resp context' (untested)

2023-10-12 01:37:56 +07:00

mrq pushed to master at mrq/ai-voice-cloning

  • 2830d1fa96 fixed setup scripts and Dockerfile to NOT use extra-index-url and instead use index-url (how this happened I don't know, since pytorch instructions use index-url), '''fixed''' phonemizing japanese for VALL-E with pykakasi

2023-10-12 00:28:10 +07:00

mrq commented on issue mrq/ai-voice-cloning#405

Does not run in Docker

Ah, I see now. The original Dockerfile was using `extra-index-url`, which will be ignored if the packages are found elsewhere (such as in the base index), especially without an explicit version…

2023-10-12 00:25:04 +07:00

mrq pushed to master at mrq/vall-e

  • 6045cbce94 added experimental option to append utterances for training target (emphasis on experimental)

2023-10-11 22:31:57 +07:00

mrq pushed to master at mrq/vall-e

  • 7facacf7c9 separated samplers into its own file, don't bother copying the logits back to the GPU after sampling, it's not necessary

2023-10-11 17:24:34 +07:00

mrq pushed to master at mrq/vall-e

  • 100dd164e6 apply phoneme cleanup in inferencing as well

2023-10-11 00:20:19 +07:00

mrq pushed to master at mrq/vall-e

  • b4405c98ea remove double spaces in the text phonemes (might have caused problems.........)

2023-10-11 00:17:26 +07:00

mrq pushed to master at mrq/vall-e

2023-10-10 23:08:53 +07:00