Purfview

Did you tried that "error_withtc_5s.wav" I've shared? >still crashes Mkay, try to add `del result` just above this line: https://github.com/SYSTRAN/faster-whisper/blob/1383fd4d3725bdf59c95d8834c629f45c6974981/faster_whisper/transcribe.py#L1473 So it would look like this: ``` python del result...

Then it must be fixed at CTranslate2, there was a try to fix it: https://github.com/OpenNMT/CTranslate2/pull/1201 >Tried this with unmodified code for faster-whisper , and the result is -> exit code...

I'll fix it in the next version.

Fixed in Pro r3.256.1

> Аnd if possible, add information about the specified language for the phrases in the JSON file Implemented in v193.1

>Please : add arguments for user defined name for output file. Why you need that? I don't see reason for this and that would add more spaghetties...

Original `faster-whisper` [this repo] doesn't have CLI. For CLI functionality look at: https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file#community-integrations >I saw some issues notice Cli or command usage of faster-whisper. Because people post in wrong repos,...

No one reported unusual "out of memory" errors on my repo, so far only in the expected scenarios like small VRAM - large model. Btw, you can try `int8`/`int8_float32` compute...

> However, in one transcription test of a 15 minute video that I ran twice on each program, it is actually 20-30% slower than `whisper-ctranslate2` running under WSL2 `Standalone Faster-Whisper`'s...

Maybe it's WSL2 issue, try to report it there -> https://github.com/Microsoft/WSL Btw, why you run it in WSL2?