Chris Ward

If I try; ``` export LD_LIBRARY_PATH="/home/user/Tools/06_MachineLearning/llama.cpp:$LD_LIBRARY_PATH" ``` I still get the same error :(

Stop being "impatient and shallow-minded"? You turned quickly. Call it how I see it.

Closed as the guys above probably want to create new github issues to track

hi @evonneng sure thing! ``` ➜ audio2photoreal git:(main) ✗ source ./.venv/bin/activate (.venv) ➜ audio2photoreal git:(main) ✗ python -m demo.demo running on... cuda:0 adding lip conditioning ./assets/iter-0200000.pt Loading checkpoints from [checkpoints/diffusion/c1_face/model000155000.pt]......

Nice one, I found this if it helps just changing it client-side; https://blog.mozilla.org/webrtc/channelcount-microphone-constraint/

And something I found for a possible solution in python; https://stackoverflow.com/questions/30401042/stereo-to-mono-wav-in-python

Okay, as a quick workaround, I updated line 241; ``` gr.Audio(sources=["microphone", "upload"] ), ``` then recorded an mono audio track in Audacity to mp3 and uploaded, seems to now be...

Okay, I got a generation, but the audio is VERY quiet - unsure what happened here, source seems fine. I'm just tuning the ffmpeg step to see if I can...

Adding ` -hwaccel cuda` to the ffpmeg header made this step almost instant

> We would appreciate a PR :) I think all python devs need the practice, but well done.