psammites
  • Joined on 2023-03-11
psammites commented on issue mrq/ai-voice-cloning#272 2023-06-19 16:47:45 +00:00
Training issue

May be related to the issue from #166, please post your console log.

psammites commented on issue mrq/ai-voice-cloning#269 2023-06-17 18:29:39 +00:00
Custom tokenizer

There's an example for Japanese in ai-voice-cloning/models/tokenizers/japanese.json and I think there are tokenizer tutorials up on huggingface.

psammites commented on issue mrq/ai-voice-cloning#268 2023-06-17 18:24:27 +00:00
Install halts

Answer Directory

psammites commented on issue mrq/ai-voice-cloning#267 2023-06-15 17:37:12 +00:00
Are conditioning latents harder to generate for larger datasets?

The latents are generated from the wav files in the subdirectory for that voice, the more you have in there the longer it will take to generate. You can adjust the Sample Batch Size in Settings…

psammites commented on issue mrq/ai-voice-cloning#265 2023-06-14 02:55:50 +00:00
Whisper transcribing isn't doing all the files

Are you using whisper or whisperx? How long are the files it's skipping?

psammites commented on issue mrq/ai-voice-cloning#260 2023-06-12 16:29:02 +00:00
ImportError: DLL load failed while importing torch_directml_native: The specified process was not found

I feel like this was not really tested on none cuda hardware.

IIRC it's been tested extensively on AMD graphics cards but ROCm (Linux), not DirectML (Windows), [as noted on the Wiki](https://g

psammites commented on issue mrq/ai-voice-cloning#261 2023-06-10 01:24:03 +00:00
Question; How to continually run from CLI

That's a new one for me. Does it happen if you revert to a previous commit?

psammites commented on issue mrq/ai-voice-cloning#261 2023-06-09 20:32:06 +00:00
Question; How to continually run from CLI

See notes from #242 regarding generation from CLI.

psammites commented on issue mrq/ai-voice-cloning#260 2023-06-09 20:29:34 +00:00
ImportError: DLL load failed while importing torch_directml_native: The specified process was not found

I've never run into that error but I use GeForce+CUDA so I can't be much help from here. All I can suggest is to try on Linux (even WSL through Windows), [according to the Wiki](https://git.ecker.t

psammites commented on issue mrq/ai-voice-cloning#260 2023-06-09 18:16:19 +00:00
ImportError: DLL load failed while importing torch_directml_native: The specified process was not found

Have you also tried with the web UI? The discussion from #242 seems to imply that CLI generation isn't fully implemented.

psammites commented on issue mrq/ai-voice-cloning#260 2023-06-09 15:36:52 +00:00
ImportError: DLL load failed while importing torch_directml_native: The specified process was not found

There was either a problem with copy/paste or you're missing a quotation mark:

python .\modules\tortoise-tts\tortoise\do_tts.py --text "Esto es una pruebita no me jodas please"

psammites commented on issue mrq/ai-voice-cloning#257 2023-06-08 13:28:58 +00:00
Anyone tried Muti-lingual for Tortoise ?

Yes, @mrq has done Japanese and @SerCeMan has done Russian, at least.

psammites commented on issue mrq/ai-voice-cloning#259 2023-06-08 13:25:57 +00:00
A Tortoise TTS Model Fine-Tuned to Speak in Russian

Does it require the prompt to be romanized or is cyrillic input supported? If so, did you have to create your own tokenizer?

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-08 04:15:22 +00:00
ModuleNotFoundError: No module named 'tortoise'

I dont know what venv is.

It's the Virtual ENVironment. It's what you activate when you run .\venv\Scripts\activate. You can tell because it appends (venv) to the beginning of your…

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-08 03:20:02 +00:00
ModuleNotFoundError: No module named 'tortoise'

Hmm, that should have worked. Try running setup-cuda.bat again (inside the venv) then update-force.bat, then start.bat, if that doesn't work delete the directory and re-clone.

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-08 02:38:54 +00:00
ModuleNotFoundError: No module named 'tortoise'

You're launching PS and then running cmd.exe in it? Why? Also you forgot the cd in front of the directory name.

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-08 01:04:11 +00:00
ModuleNotFoundError: No module named 'tortoise'

You did git clone https://git.ecker.tech/mrq/ai-voice-cloning right? Go into the directory "ai-voice-cloning" (unless you named it something else), and run .\venv\scripts\Activate. Then `git…

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-07 18:38:32 +00:00
ModuleNotFoundError: No module named 'tortoise'

You'd need to do it in the directory where you cloned the repo, preferably after activating the venv.

psammites commented on issue mrq/ai-voice-cloning#256 2023-06-07 13:32:30 +00:00
ModuleNotFoundError: No module named 'tortoise'

Try git submodule update --remote