emcodem

This leaves so many questions open... there will never be one webservice implementation that serves a general purpose. What exactly is your goal? Did you check out the existing OpenAI...

Sorry but i did not ask if you looked into python projects but into the offerings of e.g. openai themselves, e.g. the API's they provide: https://openai.com/pricing - $0.006 per minute...

There is no option for this, output is written to current working directory. To set the output path, "cd" into the output directory before calling main.exe.

"q" models are not supported (yet)

Unfortunately no official solution, as far as i know not only in this project but in none of the known open source whisper projects. Funny enough, the issue is really...

For one single source "file" it will not be possible to split onto multiple gpu's in paralell. This is because each 30s chunk's translation depends on the results from the...

I am under the impression that it is just about downloading and using the file [ggml-large-32-2.en.bin](https://huggingface.co/distil-whisper/distil-large-v2/blob/main/ggml-large-32-2.en.bin) But not sure and on the main page of the original from @AeneasZhu we...

Audio Capture Sources like Microphones are usually not locked by applications using them, so you can transcribe using whisper-constme and capture using any capture software of your choice at the...

This issue is not really related but worth to mention, it is for Whisper desktop only but i think they are different issues (e.g. one is related to colorize only)...

Win7 SP1? Does it actually work with any other model? Honestly i don't think it could work, there is far too much driver magic involved in the tensor stuff.. Also,...