stilltravelling
  • Joined on 2023-05-19
stilltravelling commented on issue ecker/ai-voice-cloning#404 2023-12-12 17:12:39 +00:00
Deepspeed - Windows (Yes I know)

I managed to build a wheel for windows using deepspeed-0.11.1 for Python 3.10 and torch 2.1. 0.11.1 allows me to change models without having to restart. Performance is pretty decent but for my…

stilltravelling commented on issue ecker/ai-voice-cloning#404 2023-10-07 06:14:59 +00:00
Deepspeed - Windows (Yes I know)

After more testing some I seem to hit OOM quite often. Think I might try WSL

stilltravelling opened issue ecker/ai-voice-cloning#404 2023-10-07 05:41:58 +00:00
Deepspeed - Windows (Yes I know)
stilltravelling commented on issue ecker/ai-voice-cloning#399 2023-10-05 12:03:16 +00:00
Nvidia Driver Woes - Super slow training

The reason for the logs was to demonstrate how long it took between each iteration using different drivers using the same data. You can see the timestamps between the iterations are much smaller…

stilltravelling commented on issue ecker/ai-voice-cloning#399 2023-09-28 16:01:04 +00:00
Nvidia Driver Woes - Super slow training

Thanks for the reply. I think you're right, I was checking dedicated GPU Memory and Shared GPU memory while using the newer drivers and Shared GPU memory seemed to be much much higher than I…

stilltravelling opened issue ecker/ai-voice-cloning#399 2023-09-28 13:09:38 +00:00
Nvidia Driver Woes - Super slow training
stilltravelling commented on issue ecker/ai-voice-cloning#247 2023-05-23 06:45:31 +00:00
Unable to start the app using start.bat

Run update.bat, wait for it to finish and then run start.bat again. The issue above was fixed in commit 805d7d35e8

stilltravelling commented on issue ecker/ai-voice-cloning#246 2023-05-23 06:43:17 +00:00
Is it possible to load a different Autoregressive Model through the Gradio API?

All confirmed working, this is turning out great. Thank you

stilltravelling closed issue ecker/ai-voice-cloning#246 2023-05-23 06:43:17 +00:00
Is it possible to load a different Autoregressive Model through the Gradio API?
stilltravelling commented on issue ecker/ai-voice-cloning#246 2023-05-22 13:01:00 +00:00
Is it possible to load a different Autoregressive Model through the Gradio API?

Thank you for doing this... There's one line in utils.py line 3480 missing the :

if autoregressive_model_path == "auto": autoregressive_model_path = deduce_autoregressive_model() else …

stilltravelling opened issue ecker/ai-voice-cloning#246 2023-05-21 21:48:22 +00:00
Is it possible to load a different Autoregressive Model through the Gradio api?
stilltravelling commented on issue ecker/ai-voice-cloning#243 2023-05-21 12:00:37 +00:00
Output sounds slow and lower pitch to tortoise-tts

Thank you, it's always nice to have the extra options.

I've generated with all new options deleted cond_latents_d1f79232.pth each time(not sure if it was necessary) and they all sound good. So…

stilltravelling commented on issue ecker/ai-voice-cloning#243 2023-05-20 07:03:23 +00:00
Output sounds slow and lower pitch to tortoise-tts

I copied a new folder with the wav files again, this time trying voice chunks of 1 rather than 5 this made him sound lower again. 10 was better but not quite there. 16 was similar.

I'll try…

stilltravelling commented on issue ecker/ai-voice-cloning#243 2023-05-19 21:51:36 +00:00
Output sounds slow and lower pitch to tortoise-tts

I've just copied the voice latents file from vanilla tortoise-tts. I had to rename the file to cond_latents_d1f79232.pth before it would work. The sound is much much better, it actually sounds…

stilltravelling commented on issue ecker/ai-voice-cloning#243 2023-05-19 16:05:59 +00:00
Output sounds slow and lower pitch to tortoise-tts

Sorry I should add, i've recorded 5 wave files for a new voice called Don. If it's not something like the sample rate, something is making it sound more generic, there are hints of his voice, but…

stilltravelling opened issue ecker/ai-voice-cloning#243 2023-05-19 15:12:19 +00:00
Output sounds slow and lower pitch to tortoise-tts