• 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
ecker pushed to master at ecker/ai-voice-cloning 2023-02-24 16:41:04 +00:00
bedbb893ac clarified import dataset settings button
ecker created branch master in ecker/tortoise-tts 2023-02-24 16:31:39 +00:00
ecker pushed to master at ecker/tortoise-tts 2023-02-24 16:31:39 +00:00
ecker commented on issue ecker/ai-voice-cloning#31 2023-02-24 16:26:00 +00:00
Colab is failing with "FileNotFoundError: [Errno 2] No such file or directory: './training/'"

No I'm stupid, I had the symlink line wrong. Should be remedied in commit f31ea9d5bc95fd5f6521ef45ca7c4d5af01e1ca9.

Change the drive mount block to:

# only run once, this will save all…
ecker commented on issue ecker/ai-voice-cloning#32 2023-02-24 16:24:29 +00:00
FileNotFoundError: [WinError 3]

Should be remedied in f31ea9d5bc95fd5f6521ef45ca7c4d5af01e1ca9. I forgot to do a simple check if something exists when importing existing settings.

But again, that button's for reusing existing…

ecker pushed to master at ecker/ai-voice-cloning 2023-02-24 16:23:37 +00:00
f31ea9d5bc oops
ecker pushed to main at ecker/tortoise-tts 2023-02-24 16:18:17 +00:00
2c7c02eb5c moved the old readme back, to align with how DLAS is setup, sorta
34b232927e Oops
d8c6739820 added constructor argument and function to load a user-specified autoregressive model
00cb19b6cf arg to skip voice latents for grabbing voice lists (for preparing datasets)
b255a77a05 updated notebooks to use the new "main" setup
Compare 282 commits »
ecker commented on issue ecker/ai-voice-cloning#32 2023-02-24 16:03:26 +00:00
FileNotFoundError: [WinError 3]

For fresh trainings, ignore the import button. The import button is for grabbing the settings from an existing training/dataset to reuse its settings. I haven't gotten around to adding it to the…

ecker commented on issue ecker/ai-voice-cloning#31 2023-02-24 16:01:20 +00:00
Colab is failing with "FileNotFoundError: [Errno 2] No such file or directory: './training/'"

I'll take a look when I can. If my assumption is correct that you did the "run all blocks in sequence" thing, then it needs the folder to be created after you mount the Drive (which is odd, since…

ecker commented on issue ecker/ai-voice-cloning#25 2023-02-24 13:14:59 +00:00
Discussion About BitsAndBytes Integration

didn't overwrite for me, I still had to copy manually.

Noted, I'll dig around for the right flags to assume overwrite (although I thought that was what /Y did). I guess that might explain…

ecker commented on issue ecker/ai-voice-cloning#30 2023-02-24 13:08:45 +00:00
MIOpen(HIP): Error [EvaluateInvokers] /MIOpen/src/gemm_v2.cpp:648: rocBlas error encountered

mmm

I'm not too sure what would cause ROCm specific errors. Are you using the default model or a finetuned one? I'd imagine a finetuned one might throw some issues, but I wouldn't know.

ecker pushed to master at ecker/ai-voice-cloning 2023-02-24 13:05:20 +00:00
ecker commented on issue ecker/ai-voice-cloning#27 2023-02-24 12:59:57 +00:00
Feature request: Refresh model directory/dropdown button

(Finally) added in commit f6d0b66e1009d5a8c797219761eed1033a4735ce.

It'll search for the finetune folders in the ./training/ folder, so you won't even need to copy them now.

ecker closed issue ecker/ai-voice-cloning#27 2023-02-24 12:59:57 +00:00
Feature request: Refresh model directory/dropdown button
ecker pushed to master at ecker/ai-voice-cloning 2023-02-24 12:58:52 +00:00
f6d0b66e10 finally added model refresh button, also searches in the training folder for outputted models so you don't even need to copy them
ecker commented on issue ecker/ai-voice-cloning#25 2023-02-24 03:20:19 +00:00
Discussion About BitsAndBytes Integration

Did you copy the files from .\ai-voice-cloning\dlas\bitsandbytes_windows\ into .\ai-voice-cloning\venv\Lib\site-packages\bitsandbytes\?

The setup-cuda.sh script should do it automagically…

ecker commented on issue ecker/ai-voice-cloning#29 2023-02-23 23:24:12 +00:00
Suggestion: More user-friendly labels in "Generate Configuration"

Remedied in commit 1e0fec4358a11bac2cf20cef05d3e890638ee7c5. I renamed it to "Print/Save Frequency (in epochs)".

ecker closed issue ecker/ai-voice-cloning#29 2023-02-23 23:24:12 +00:00
Suggestion: More user-friendly labels in "Generate Configuration"
ecker pushed to master at ecker/ai-voice-cloning 2023-02-23 23:22:45 +00:00
1e0fec4358 god i finally found some time and focus: reworded print/save freq per epoch => print/save freq (in epochs), added import config button to reread the last used settings (will check for the output folder's configs first, then the generated ones) and auto-grab the last resume state (if available), some other cleanups i genuinely don't remember what I did when I spaced out for 20 minutes
ecker commented on issue ecker/ai-voice-cloning#29 2023-02-23 20:12:41 +00:00
Suggestion: More user-friendly labels in "Generate Configuration"

No you're right, it implies it'll do it within an epoch, rather than every epoch. desu it was originally labeled "Print Frequency" and "Save Frequency" when it was just in terms of iterations, but…