News for hackers. Stuff that matters.

A comment on Complete silence is always hallucinated as "ترجمة نانسي قنقر" in Arabic. Parent comment

Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by cyp0633 on Tuesday July 22, 2025 @06:50AM (#44645346)
That is not the case here - I never encountered this with whisper-large-v3 or similar ASR models. Part of the reason, I guess, is that those subs are burnt into the movie, which makes them hard to extract. Standalone subs need the corresponding video resource to match the audio and text. So nothing is better than YouTube videos which are already aligned.
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by simsla on Tuesday July 22, 2025 @08:24AM (#44646000)
At least for English, those "fansubs" aren't typically burnt into the movie*, but ride along in the video container (MP4/MKV) as subtitle streams. They can typically be extracted as SRT files (plain text with sentence level timestamps).

*Although it used to be more common for AVI files in the olden days.

[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by Maken on Tuesday July 22, 2025 @09:27AM (#44646621)
SRT is ancient. Nowadays everyone uses ASS subtitles which can be randomly styled.
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by simsla on Tuesday July 22, 2025 @09:35AM (#44646709)
In general? In the past I've known ASS to be used a lot for things like anime, but less for live action shows.
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by Maken on Tuesday July 22, 2025 @11:42AM (#44648585)
I have also found them inside mkvs as the subtitle track. I think SRT was the default because most content was ripped from DVD/BD, but now most of the content is from streaming sources and you need to convert the subtitles anyway.
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by conradev on Tuesday July 22, 2025 @09:46AM (#44646836)
WebVTT (a SubRip successor) is probably more widely used than ASS
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by Maken on Tuesday July 22, 2025 @11:33AM (#44648429)
By legit providers, probably.
[ Parent | on HN ]
Re:Complete silence is always hallucinated as "ترجمة نانسي ق... by ethbr1 on Tuesday July 22, 2025 @09:21AM (#44646545)
flashbacks of trying to track down subs sync’d to a specific release
[ Parent | on HN ]