accountts commented on issue mrq/ai-voice-cloning#113
Generated voices from training data always garbled.... but works fine using tortoise-tts-fast ... (?)It's the same on whisper for me
accountts commented on issue mrq/ai-voice-cloning#113
Generated voices from training data always garbled.... but works fine using tortoise-tts-fast ... (?)> The biggest problem I'm having when it comes to transcription, even when using WhisperX, is the transcribed text having a full sentence, but the audio having the first or last word or two cut…
accountts commented on issue mrq/ai-voice-cloning#100
! POSSIBLE NEW ISSUES !I don't know if it's related, but it's now 4 times "slower" for each preset (for instance, ultra used to set 16 samples that amounted to 4 autoregressive steps, now it sets 16 samples and 16…
accountts commented on issue mrq/ai-voice-cloning#103
! RETRAIN YOUR MODELS !Unless I'm mistaken you did not implement the same way, you set -sub where he set sub `return text_logits[:, :sub]` vs `return text_logits[:, :-sub]` Is this intended ? I still don't…
accountts commented on issue mrq/ai-voice-cloning#60
Share your models> Where do you place the models , I am a bit confused about where finetuned models go and where just models go Place your custom models here './training/finetunes/{voice}.pth' https://git.eck…
accountts commented on issue mrq/ai-voice-cloning#81
Train.py Traceback ErrorThat line tries to load your training yaml file. I assume you're launching train.bat You have to pass the yaml file to train.bat like this `train.bat "./training/yourvoice/train.yaml"`
accountts commented on issue mrq/tortoise-tts#9
Keeping gradio from phoning homeI'm still getting attempts at some outside connections ``` Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: <Handle _ProactorBasePipeTransport._call_connec…
accountts commented on issue mrq/ai-voice-cloning#25
Discussion About BitsAndBytes IntegrationHi I had the same error. `copy .\dlas\bitsandbytes_windows\* .\venv\Lib\site-packages\bitsandbytes\. /Y` didn't overwrite for me, I still had to copy manually. Now it's training fine on…
accountts commented on issue mrq/ai-voice-cloning#11
Cuda out of memoryI had better results by regenerating voice latents after switching the model to the trained one. Are voice latents tied to the model maybe ?
accountts commented on issue mrq/ai-voice-cloning#8
"IndexError: list index out of range" at the first step of training in ./dlas/codes/trainer/steps.py", line 214, in do_forward_backwardSame result as you here. This particular issue seems fixed but I still can't get it to run on 8GB VRAM, always OOM. Maybe the model is too big to be trained on 8GB.
accountts closed issue mrq/ai-voice-cloning#9
Can't get finetuned model to load using the UIaccountts commented on issue mrq/ai-voice-cloning#9
Can't get finetuned model to load using the UIyep, that fixed it.
accountts opened issue mrq/ai-voice-cloning#9
Can't get finetuned model to load using the UIaccountts commented on issue mrq/ai-voice-cloning#8
"IndexError: list index out of range" at the first step of training in ./dlas/codes/trainer/steps.py", line 214, in do_forward_backwardI set 50 iterations just to try to get it going on my GPU. I ended up training on tts-fast colab and stopped it at 600 this is the yaml that colab created https://pastebin.com/E9wNJYmt then…
accountts opened issue mrq/ai-voice-cloning#8
"IndexError: list index out of range" at the first step of training in ./dlas/codes/trainer/steps.py", line 214, in do_forward_backwardaccountts closed issue mrq/tortoise-tts#36
Result files still don't increment properly for meaccountts commented on issue mrq/tortoise-tts#36
Result files still don't increment properly for meThanks that fixed it. Cheers
accountts commented on issue mrq/tortoise-tts#36
Result files still don't increment properly for meWelp, still the same for me. Emptied the result directory for this voice, generated 3 times, and ended up with only files 00000 and 00001, with second attempt overwritten. Only thing suspicious…
accountts opened issue mrq/tortoise-tts#36
Result files still don't increment properly for meaccountts opened issue mrq/tortoise-tts#15
Shouldn't Cuda have priority over DML ?