n8bot

If that colab doesn't work anymore, I have no idea. I abandoned that process and now just do local inferencing. Here are my latest steps which rely purely on (mini)conda:...

Attached is a sample of the output of some of the voices. ## Newest samples: Here is a demonstration of all the voices, as well as a failure of the...

I did not do extensive testing with reduced numbers of these particular clips. They immediately worked so well, particularly the speech-only ones, that I left it as is with all...

I removed all binary file redundancy. Now there are only redundant markdown files with license and instructions for constructing subset voices.

I just did a test with an "angry" subset voice, and the results are way less consistent. The voice completely changes. So it does appear that the sheer volume of...

By the way, I have no problem if you decide not to include this in your repo. It requires no maintenance so I can easily patch this on top of...

It's interesting, when I use the "angry" subset of clips for a voice, the consistency is much lower overall — random female voices and other voices pop up in clips....

Yeah, some voices are better or worse than others. I have made a pull request to add more voices: https://github.com/neonbjb/tortoise-tts/pull/425 Each voice has dozens of audio clips. Try them out...

Use conda. [Download miniconda](https://docs.conda.io/en/latest/miniconda.html) Then open the newly installed "Anaconda prompt" app from the start menu. Copy and paste all these commands: ``` conda create --name tortoise python=3.9 numba inflect...

I was thinking of trying to get that one working as well. I do not currently have any working methods for tts-fast fork.