Nicholas

Looking for a better free service than RVC's V2V--how is this V2V service? Thanks! Will donate if it's good :)

Mojo version?

2

https://github.com/tairov/llama2.mojo Imagine 250x speed on the original...

Installation went perfectly, but GPU runtime will not work -- only CPU is used

10

To make ToirToiSe say the word "Hi." On the fastest setting, 1/2hr -- on 0% of my GPU is utilized, I can run the largest SD models whilst this inferencing...

I'd love to use Piper for my program but there are no safetensor models for the voice models, so I can't guarantee people will be safe to use it. Can...

Added your repo in the update which included one of its files, but if you have any specific website you'd like attributed, a name, etc. please let me know. Use:...

[Bug] ModuleNotFoundError: No module named 'TTS' (From inside the TTS folder)

1

### Describe the bug File "[redacted]\TTS-dev\TTS\demos\xtts_ft_demo\xtts_demo.py", line 14, in from TTS.demos.xtts_ft_demo.utils.formatter import format_audio_list ModuleNotFoundError: No module named 'TTS' This is from within the TTS file itself, using the demo inside...

Please save Github some bandwidth and list average VRAM usage/minimum VRAM requirements per generation type on the home page. Thanks!

For those having issues with getting their fine tunes to develop/load in the xtts_finetune_webui.py

1

I've found a solution. Use the collab version to produce your finely tuned model (youtube keyword xtts fine tuning -- very simple collab instructions) Now once you've downloaded the complete...

In the bottom left-hand corner, in fact, I jumped out of my seat for a moment, having yet to use that feature, after spending a few days looking for a...

set you could set this up so that different voices are trigger based on different 'sandwiched characters' (if you're familiar with python reg.ex -- reg.ex code) Bob is triggered in...