tigros / Whisperer

Batch speech to text using OpenAI's whisper.
256 stars 24 forks source link

Meaningless word repetition problem #29

Closed kbuwel closed 1 year ago

kbuwel commented 1 year ago

When a video file over 10 minutes is loaded and converted to srt, txt, etc. using voice recognition, tens of thousands of lines of meaningless words are written. For example, [end] [baby crying] [everyone] [fire sound], etc. Words that are not in the video file are written endlessly. System specifications are as follows: AMD 5900x RTX3060 12GB G.SKILL DDR4 64GB xmp 2.0 870evo 2TB SSD Too many meaningless words written. Can you solve this problem?

tigros commented 1 year ago

this is a known issue, it can happen sometimes, you can search issues in const-me, openai, ggerganov repos, it's all over the place.

maybe in about a year it will finally be resolved.