eloop001

> hi [@balisujohn](https://github.com/balisujohn) can you provide script to convert tortoise to ggml format, thank you `import torch import numpy as np voice = "your_voice.pth" # Replace with your actual file...

> Most scripts have an option to select the device: > >  > > If not, then you can set an environment variable to tell PyTorch to not use...

The download speed for voicefixer is for some reason very low.

> Sorry, I misunderstood, however, [this seems similar](https://git.ecker.tech/mrq/tortoise-tts/issues/35#issuecomment-145)? > > I'll try doing [this](https://github.com/neonbjb/tortoise-tts/issues/48) and run the UI 2 times, pointing them to different CUDA devices. I have had great...

Hi Matt You can avoid this by adding pipe | sign in the text. If the application sees you have these signs it will not insert them from the tokenizer.py...

It's certainly better to do it after a punctuation mark. I ran into the issue that sentences between punctuation marks would still need to be shorter. You can look in...

Just an example. It would be trivial to split on punctuation marks, because of Kafka's writing style, but other texts are not that semantically graceful. https://www.gutenberg.org/cache/epub/7849/pg7849.txt Den man. 1. maj...

I know the answer to this one. Simply delete the line in requirements.txt that has to do with BigVGAN.... it's around line 36 as far as I remember.

I just delete the line. It has no effect. fre. 28. apr. 2023 18.00 skrev embanot ***@***.***>: > I don't see any line in requirements.txt that has to do with...

Hi Yes, I believe there is. My hypothesis is that the conditional_latents model that one trains and that outputs the .pth file you put in the voices folder (instead of...