Gary James Nave (Cognibuild)

All Sorts of Issues Executing (WSL and Windows)

17

Hey guys, So I'm having a difficult time getting certain files t but does not work on wsl when I leave it as a lama file o load. Here's one...

AssertionError: Could not resolve compression model checkpoint path: ./pretrained_models/encodec_4cb2048_giga.th

2

I had this working on a previous install and now getting this when attempting to load models. Any ideas? Dora directory: /tmp/audiocraft_cognibuild Traceback (most recent call last): File "/home/cognibuild/miniconda3/envs/voicecraft/lib/python3.9/site-packages/gradio/queueing.py", line...

This is how you solve "Torch installed w/out Cuda" error

4

It's a procedural issue. The problem is that you have to install the cuda toolkit first: 1) conda create --name ifw 2) activate ifw 3) conda config --append channels nvidia...

having onnx problems and really dont want to upgrade my CUDA

LLMLoader ckpt_name is undefined

1

I've attempted to download the llm and place it in the models/llm folder but does nto show up - nor do any other llms I put there to test to...

Coordinates no longer available

2

Am i missing something? Just a couple days ago I was able to install adn get coordiantes along with the parsed screen elements. Was that removed?

Newest Update seems to have broken webui/manage.py

7

### Self Checks - [X] This template is only for bug reports. For questions, please visit [Discussions](https://github.com/fishaudio/fish-speech/discussions). - [X] I have thoroughly reviewed the project documentation (installation, training, inference) but...