Vadim Peretokin

Thanks, the need for the event makes sense! I see it's making use of 0's and 1's - could you describe how that works so @Mudlet/lua-interface can review it appropriately?

Otherwise looks solid to me.

/refresh links

`diffusion_model.h5` is also a large file that needs to be downloaded, and perhaps downloaded first. Not sure where it comes from, though.

Still broken, unfortunately :(

I'm getting the same using a clean build on e9cd7e0869edb09f73dc2d79d0256425e7af55f9, and the workaround worked.

Same on RTX 4080, fails to launch: ``` => [2/3] RUN python3 -m pip install --disable-pip-version-check -U torch --extra-index-url https://download.pytorch.org/whl/cu116 188.7s => [3/3] RUN python3 -m pip install --disable-pip-version-check -U...

I get the same (RTX 4080) however it does actually work: ``` fauxpilot-triton-1 | ============================= fauxpilot-triton-1 | == Triton Inference Server == fauxpilot-triton-1 | ============================= fauxpilot-triton-1 | fauxpilot-triton-1 | NVIDIA...

The trick in https://github.com/guillaumekln/faster-whisper/issues/153#issuecomment-1510218906 is not working for me, what am I doing wrong? ```python (faster-whisper) vadi@barbar:~$ pip install nvidia-cublas-cu11 nvidia-cudnn-cu11 Requirement already satisfied: nvidia-cublas-cu11 in ./Programs/miniconda3/envs/faster-whisper/lib/python3.10/site-packages (11.11.3.6) Requirement already...

It did. Thanks!