Transcription stopped halfway about whisper-standalone-win

[Purfview]

I reproduced this issue on my side. Later I'll check what can be done about it.
Interestingly, this hallucination starts on the advertisement.

[Purfview]

It doesn't stuck with -beam_size=5 option.

Ad at start/end is still ignored, probably models are trained to ignore that ad. Btw tiny and base models transcribe that ad.

[nhan000]

I added the parameter you gave me, so the code is

whisper-faster "C:\Users\ntnha\Videos\4K Video Downloader\Carl Sagan Astronomer of the People.mp4" --language en --model large-v2 --batch_recursive true --compute_type=int8

It ran on cuda

And it still stopped at the same location

[Purfview]

Check if .srt subtitle file is created. [when you think that it's "stopped"]

[nhan000]

The srt file was created and the later half was missing, same as the timestamp in the command prompt.

[Purfview]

Do you run it on cuda? If yes then try --compute_type=int8 parameter.

[nhan000]

Thanks for looking into this, and separately, thanks for making this program. Very noob-friendly for people who are not very techy like me.

The video has 3 advertisement segments:

• One at the beginning that Whisper Standalone doesn't transcribe for both mp4 and mp3 files.
• One at the middle (13:19) that it transcribes in the mp3 file but stopped for the mp4 file.
• One at the end (26:46) that it also doesn't transcribe in the mp3 file.

[nhan000]

Thanks a lot! I will keep the beam size parameter in mind and change it around when I ran into issues.