Bluebomber182
  • Joined on 2023-03-06
Bluebomber182 opened issue mrq/ai-voice-cloning#337 2023-08-23 01:09:32 +00:00
Starting the vall-e backend crashes
Bluebomber182 opened issue mrq/ai-voice-cloning#324 2023-08-09 08:15:17 +00:00
Does bark feature fine tuning?
Bluebomber182 commented on issue mrq/vall-e#2 2023-04-14 20:58:52 +00:00
ValueError: No valid path is found for training.

I updated vall-e and I now longer get the os error message. But now I get this error message. I made a custom folder inside the data folder. Here is a zip file of the custom folder. https://files.…

Bluebomber182 opened issue mrq/vall-e#2 2023-04-14 07:19:03 +00:00
NameError: name 'os' is not defined
Bluebomber182 closed issue mrq/ai-voice-cloning#202 2023-04-13 20:06:33 +00:00
How do I regenerate the same input prompt?
Bluebomber182 commented on issue mrq/ai-voice-cloning#202 2023-04-13 20:05:36 +00:00
How do I regenerate the same input prompt?

How do I close this issue?

Bluebomber182 commented on issue mrq/ai-voice-cloning#202 2023-04-13 19:32:17 +00:00
How do I regenerate the same input prompt?

I set the seed anywhere from -10 to 100 and each output file is literally the same as prevoius one.

Bluebomber182 opened issue mrq/ai-voice-cloning#202 2023-04-12 19:17:11 +00:00
How do I regenerate the same input prompt?
Bluebomber182 commented on issue mrq/ai-voice-cloning#60 2023-04-12 01:53:51 +00:00
Share your models
Bluebomber182 commented on issue mrq/ai-voice-cloning#121 2023-04-11 22:57:51 +00:00
Cuda OOM error when running start.bat

I wanna give out helpful info if you happen to use a nvidia graphics card that has 6GB or more of VRAM and you set the batch size to low and you still get this error message `RuntimeError: CUDA…

Bluebomber182 commented on issue mrq/ai-voice-cloning#129 2023-03-17 02:44:29 +00:00
need help, trying to train voice but just sounds like a generic male tts voice?

I have the same problem too. I created a Merida dataset with wav files that are more than 0.6 seconds and less than 11 seconds. I trained it up to 2160 steps. With 29 seconds worth of samples, the…

Bluebomber182 commented on issue mrq/ai-voice-cloning#127 2023-03-15 03:24:25 +00:00
Error On Install Dependencies; expected?

Where can I find the latest version? I downloaded this file here. https://git.ecker.tech/mrq/ai-voice-cloning/raw/branch/master/notebook_colab.ipynb

Bluebomber182 commented on issue mrq/ai-voice-cloning#127 2023-03-15 01:26:07 +00:00
Error On Install Dependencies; expected?

I get this error message in Google Colab. Why? !source ./venv/bin/activate /bin/bash: ./venv/bin/activate: No such file or directory

Bluebomber182 commented on issue mrq/ai-voice-cloning#60 2023-03-09 00:03:08 +00:00
Share your models

Louise Belcher. I also included a dataset of wav files and a train.txt file. Can someone tell me how to create folders in huggingface? https://huggingface.co/Bluebomber182/Louise-Belcher

Bluebomber182 commented on issue mrq/ai-voice-cloning#70 2023-03-08 00:29:10 +00:00
Question, why does my model produce bad output?

Another question, I made a dataset of Judy Hopps, and I get output files of british accents with both the finetune model and the stock autoregressive.pth file. Why is that? Here is a link for the…

Bluebomber182 opened issue mrq/ai-voice-cloning#70 2023-03-06 03:35:17 +00:00
Question, why does my model produce bad output?