ecker
18 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 2022-10-10
Repositories
10
 Projects Packages Public Activity Starred Repositories
ecker closed issue ecker/ai-voice-cloning#55 2023-03-03 13:55:17 +00:00
err
ecker pushed to main at ecker/tortoise-tts 2023-03-03 13:53:58 +00:00
06bdf72b89 load the model on CPU because torch doesn't like loading models directly to GPU (it just follows the default vocoder loading behavior)
ecker pushed to master at ecker/tortoise-tts 2023-03-03 13:53:49 +00:00
06bdf72b89 load the model on CPU because torch doesn't like loading models directly to GPU (it just follows the default vocoder loading behavior)
ecker commented on issue ecker/ai-voice-cloning#54 2023-03-03 13:12:58 +00:00
Getting "RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR" while training

WavFileWarning: Chunk (non-data) not understood, skipping it.

Are just the same type of "non-error" that you get from inferencing/generating normally; they're pretty harmless.

fatal :…

ecker commented on issue ecker/ai-voice-cloning#37 2023-03-03 07:25:08 +00:00
[Feature request] Add support for whisper.cpp

I tried the other day on Windows but absolutely couldn't get it to be happy. I imagine if it's giving me hell, it'd be hell for any other Windows user to try and get it to compile anyhow. Oh…

ecker pushed to master at ecker/ai-voice-cloning 2023-03-03 07:23:24 +00:00
9fb4aa7917 validated whispercpp working, fixed args.listen not being saved due to brainworms
ecker commented on issue ecker/ai-voice-cloning#52 2023-03-03 06:59:44 +00:00
Implement BigVGAN

Very nice, implemented in mrq/tortoise-tts commit aca32a71f7, and added a toggle (default enabled) in commit 740b5587df1…

ecker closed issue ecker/ai-voice-cloning#52 2023-03-03 06:59:44 +00:00
Implement BigVGAN
ecker deleted branch BigVGAN from ecker/tortoise-tts 2023-03-03 06:46:08 +00:00
ecker pushed to master at ecker/tortoise-tts 2023-03-03 06:46:01 +00:00
2ba0e056cd attribution
ecker pushed to main at ecker/tortoise-tts 2023-03-03 06:45:46 +00:00
2ba0e056cd attribution
ecker pushed to master at ecker/ai-voice-cloning 2023-03-03 06:39:44 +00:00
740b5587df added option to specify using BigVGAN as the vocoder for mrq/tortoise-tts
ecker pushed to master at ecker/tortoise-tts 2023-03-03 06:31:24 +00:00
aca32a71f7 added BigVGAN in place of default vocoder (credit to https://github.com/deviandice/tortoise-tts-BigVGAN)
ecker pushed to main at ecker/tortoise-tts 2023-03-03 06:31:18 +00:00
aca32a71f7 added BigVGAN in place of default vocoder (credit to https://github.com/deviandice/tortoise-tts-BigVGAN)
ecker pushed to master at ecker/ai-voice-cloning 2023-03-03 05:51:28 +00:00
68f4858ce9 oops
ecker commented on issue ecker/ai-voice-cloning#53 2023-03-03 05:49:49 +00:00
Error when generating voice

Whoops, I guess I forgot to update that line. I'll push a fix in a few minutes.

ecker created branch BigVGAN in ecker/tortoise-tts 2023-03-03 05:30:37 +00:00
ecker pushed to BigVGAN at ecker/tortoise-tts 2023-03-03 05:30:37 +00:00
d21ceb3d9a BigVGAN (credit to https://github.com/deviandice/tortoise-tts-BigVGAN)
ecker commented on issue ecker/ai-voice-cloning#46 2023-03-03 04:53:32 +00:00
Getting error "cuDNN error: CUDNN_STATUS_MAPPING_ERROR"

Alrighty, so I got some good-ish news for you:

  • I seem to be wrong about the absolute minimum requirement for BitsAndBytes. It appears to have some support for Kepler and beyond (`8-bit…
ecker commented on issue ecker/ai-voice-cloning#52 2023-03-03 04:43:20 +00:00
Implement BigVGAN

Naisu, I'll play around with it whenever I get a chance to (probably tomorrow evening).

If you don't mind, to make my life a little easier (and it'll retain credit to you in the commit…