montvid

One year later not fixed yet :P could at least someone update the faq with this instruction so people can find how to configure that? https://github.com/ollama/ollama/issues/5965#issuecomment-2252354726

Ollama still does not work and llama.cpp on q8 is bad. Use vllm. https://github.com/allenai/olmocr/issues/347

Source build with cuda 13 and torch 2.9 or 2.10 does no work for me too. 64 gb ram 32 cpu.

https://github.com/mjun0812/flash-attention-prebuild-wheels work fine too.

pyannote have their own VAD as I understand - maybe one could use it? From https://github.com/m-bain/whisperX > Valuable VAD & Diarization Models from [pyannote audio][https://github.com/pyannote/pyannote-audio] From https://github.com/shashikg/WhisperS2T > [NVIDIA NeMo...

a fix was merged for faster whisper - maybe that solves the problem? https://github.com/SYSTRAN/faster-whisper/pull/921

Faster-whisper programmers say it is not a VAD issue maybe here: [ After using VAD, the start and end times of the recognized segments are incorrect #1119 ]https://github.com/SYSTRAN/faster-whisper/issues/1119

The library does not build on python 3.12 too https://github.com/Anjok07/ultimatevocalremovergui/issues/1578#issuecomment-2525067265 ``` pipx >(analyze_pip_output:311): pip seemed to fail to build package: audioread==3.0.0 Some possibly relevant errors from pip install: error: subprocess-exited-with-error...

> https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size the faq needs to be updated with your example as it took a lot of time to understand and configure the solution as it is NOT mentioned in...

I got some audio files from a dvd vob file extracted with ffmpeg and got this error. Tried to extract the vob file to mkv and got he same error....