kittsil

There are outstanding issues with this PR: 1. I have not found the definition of the 224 context token length. 2. It prepends the `initial_prompt` to itself before enough tokens...

@ryanheise Thank you for your input; it was helpful. Do you mind providing any additional feedback? --- Aside: I did find the left-slice in the code, and it turns out...

> how errors like this can be fixed? > >  @FurkanGozukara, that's an issue with `whisper`, not with your prompt. You can try setting `compression_ratio_threshold` lower; I have found...

@drake7707 's great Dockerfile worked for me, except that: 1. I am running `python 3.10`, whereas the base image has `python 3.11`. I explicitly installed `python3.10` with `apt-get` and then...

I am not sure that this is a valuable change. While it is not a robust benchmark, I did do an experiment on my local machine. 10x `log_mel_spectrogram()` on a...

@take0x, I was using my GPU to transcribe. > What is important is that the device specified in `load_model()` should be used when transcribing, rather than the actual benchmark result....