mrchucksneed
  • Joined on 2023-02-21
mrchucksneed commented on issue mrq/ai-voice-cloning#25 2023-03-02 01:44:24 +00:00
Discussion About BitsAndBytes Integration

Naisu, I'll edit the setup-rocm.sh install script to have it install that.

do get this "error" now when launching, might need removing or contextualising for AMD users

CUDA SETUP:…
mrchucksneed commented on issue mrq/ai-voice-cloning#25 2023-03-02 01:17:59 +00:00
Discussion About BitsAndBytes Integration

If you want to be a guinea pig, run:

source ./venv/bin/activate
pip3 uninstall bitsandbytes
pip install git+https://github.com/broncotc/bitsandbytes-rocm
deactivate

mrchucksneed commented on issue mrq/ai-voice-cloning#25 2023-03-02 01:03:38 +00:00
Discussion About BitsAndBytes Integration
[Training] [2023-03-02T01:01:30.089720] 
[Training] [2023-03-02T01:01:30.089843]   0%
mrchucksneed commented on issue mrq/ai-voice-cloning#30 2023-03-02 00:32:29 +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…

mrchucksneed commented on issue mrq/ai-voice-cloning#30 2023-02-24 12:53:41 +00:00
MIOpen(HIP): Error [EvaluateInvokers] /MIOpen/src/gemm_v2.cpp:648: rocBlas error encountered
MIOpen Error: /MIOpen/src/gemm_v2.cpp:648: rocBlas error encountered
Traceback (most recent call last):
  File "/home/linuxuser/Documents/ai-voice-cloning/src/webui.py", line 54, in…
mrchucksneed opened issue mrq/ai-voice-cloning#30 2023-02-24 12:41:03 +00:00
MIOpen(HIP): Error [EvaluateInvokers] /MIOpen/src/gemm_v2.cpp:648: rocBlas error encountered
mrchucksneed commented on issue mrq/ai-voice-cloning#21 2023-02-21 22:19:11 +00:00
gradio.exceptions.Error: 'torch.cat(): expected a non-empty list of Tensors'

Oops, a slight oversight. Should be fixed in commit fefc7aba0388d061a2db37cd74ebef7a9172439b.

I'm either really thick or I'm missing something, when I read samples in the UI, I'm actually…

mrchucksneed commented on issue mrq/ai-voice-cloning#21 2023-02-21 21:59:02 +00:00
gradio.exceptions.Error: 'torch.cat(): expected a non-empty list of Tensors'

Should be fixed in commit 9e64dad785bc6d6e0e948784b27028d5d4746e25. I can't do any tests for it on my 2060 since I can't increase it's batch size all that much for higher numbers.

Reading…
mrchucksneed commented on issue mrq/ai-voice-cloning#21 2023-02-21 21:41:12 +00:00
gradio.exceptions.Error: 'torch.cat(): expected a non-empty list of Tensors'

Can you provide a full stack trace? I'm pretty sure I won't need one, since I'll just clamp down the batch size to the sample size. Actually, I should be able to replicate it.

mrchucksneed commented on issue mrq/ai-voice-cloning#21 2023-02-21 21:32:49 +00:00
gradio.exceptions.Error: 'torch.cat(): expected a non-empty list of Tensors'

That's from it automatically deducing your batch size. On DirectML, there doesn't seem to be an (easy) way to get VRAM capacity, but it's exposed with ROCm, so it's using larger batch sizes. I…

mrchucksneed opened issue mrq/ai-voice-cloning#21 2023-02-21 20:55:00 +00:00
gradio.exceptions.Error: 'torch.cat(): expected a non-empty list of Tensors'
mrchucksneed commented on issue mrq/ai-voice-cloning#20 2023-02-21 20:36:18 +00:00
python: command not found

Should be remedied in commit f119993fb5724dafe0e68cf0da360f3ab6c2f61d.

Can confirm remedied and holy moly is ROCm way faster. Thank you so much.

mrchucksneed opened issue mrq/ai-voice-cloning#20 2023-02-21 20:16:51 +00:00
python: command not found
mrchucksneed commented on issue mrq/ai-voice-cloning#16 2023-02-21 18:20:39 +00:00
AttributeError: module 'ffmpeg' has no attribute 'Error'

Almost forgot the venv. Should be as easy as deleting your old one and dropping this in place.

I might have to download a Linux distro and test it…

mrchucksneed commented on issue mrq/ai-voice-cloning#16 2023-02-21 15:41:21 +00:00
AttributeError: module 'ffmpeg' has no attribute 'Error'

Took a small bit of elbow grease to get it to work (for simplicity I just thrown it at C:\Tortoise\ai-voice-cloning\ so I don't need to edit some paths, and had to edit .\venv\pyvenv.conf

mrchucksneed commented on issue mrq/ai-voice-cloning#16 2023-02-21 04:33:02 +00:00
AttributeError: module 'ffmpeg' has no attribute 'Error'

Any way you can zip up and send your venv folder? I might be able to figure it out if I can probe the current state.

Windows 10, [...] RX 6900 XTXH

Actually, not to rain on…

mrchucksneed opened issue mrq/ai-voice-cloning#16 2023-02-21 03:36:50 +00:00
AttributeError: module 'ffmpeg' has no attribute 'Error'