demonauthor
  • Joined on 2023-03-25
demonauthor commented on issue mrq/ai-voice-cloning#197 2023-04-15 12:46:21 +00:00
Epochs, iterations, and datasets

Transcriptions are accurate. Having the same problem generating a British accent now, which seems weird.

demonauthor commented on issue mrq/ai-voice-cloning#197 2023-04-11 21:53:56 +00:00
Epochs, iterations, and datasets

Will check again, but at first glance, they looked good.

demonauthor commented on issue mrq/ai-voice-cloning#197 2023-04-11 20:23:24 +00:00
Epochs, iterations, and datasets

That all makes sense. I have found more epochs leads to cleaner audio...but I'm still getting a smoothed out version of the voice when I generate. What I want is a thick accent like the dataset…

demonauthor opened issue mrq/ai-voice-cloning#197 2023-04-09 15:32:56 +00:00
Epochs, iterations, and datasets
demonauthor commented on issue mrq/ai-voice-cloning#193 2023-04-09 02:26:08 +00:00
Can you add to an already trained model?

I did an additional 500 iterations with a new dataset of the same voice over the original model I trained as the Source Model... No change at all. Getting an accent to shine through is difficult.…

demonauthor commented on issue mrq/ai-voice-cloning#193 2023-04-07 15:51:43 +00:00
Can you add to an already trained model?

Crap, nevermind. I see it in the Config settings.

demonauthor commented on issue mrq/ai-voice-cloning#193 2023-04-07 15:48:37 +00:00
Can you add to an already trained model?

Thanks for that. I'll give it a shot. When you say "Source Model" is that the Autoregressive model under settings?

demonauthor commented on issue mrq/ai-voice-cloning#183 2023-04-06 23:52:04 +00:00
generating voice clip is so much slower compared to using original Tortoise TTS

I am finding this very slow as well. It seems the same file using the same voice folder and model in DLAS generates significantly faster than here in the AI-Voice-Cloning using the same ultra-fast…

demonauthor opened issue mrq/ai-voice-cloning#193 2023-04-06 23:45:32 +00:00
Can you add to an already trained model?
demonauthor closed issue mrq/ai-voice-cloning#179 2023-03-27 16:30:18 +00:00
Can validate a training configuration, but can't save it.
demonauthor commented on issue mrq/ai-voice-cloning#179 2023-03-27 15:15:20 +00:00
Can validate a training configuration, but can't save it.

It was also missing /models/tortoise/train_diffusion_vocoder_22k_level.yml so I restored that as well... Now it seems to be training.

demonauthor commented on issue mrq/ai-voice-cloning#179 2023-03-27 15:00:55 +00:00
Can validate a training configuration, but can't save it.

I did run update.bat. Will try the git restore...

demonauthor commented on issue mrq/ai-voice-cloning#179 2023-03-27 11:27:29 +00:00
Can validate a training configuration, but can't save it.

I ran the initial setup script. "setup-cuda.bat"

Is there a different one?

demonauthor opened issue mrq/ai-voice-cloning#179 2023-03-26 21:26:49 +00:00
Can validate a training configuration, but can't save it.
demonauthor closed issue mrq/ai-voice-cloning#178 2023-03-26 20:58:41 +00:00
Would love a hand-holding tutorial on preparing a dataset...
demonauthor commented on issue mrq/ai-voice-cloning#178 2023-03-26 20:58:35 +00:00
Would love a hand-holding tutorial on preparing a dataset...

Dangit. I just found that one and was going to post it here... Thanks.

demonauthor opened issue mrq/ai-voice-cloning#178 2023-03-26 20:39:57 +00:00
Would love a hand-holding tutorial on preparing a dataset...