(ffmpeg.org)

985 points gyan | 5 comments | 22 Aug 25 15:22 UTC | HN request time: 0.873s | source

1. oblio ◴[22 Aug 25 15:34 UTC] No.44985864[source]▶

First of all: congratulations!!!

Secondly, just curious: any insiders here?

What changed? I see the infrastructure has been upgraded, this seems like a big release, etc. I guess there was a recent influx of contributors? A corporate donation? Something else?

replies(1): >>44985903 #

2. exprez135 ◴[22 Aug 25 15:39 UTC] No.44985903[source]▶

>>44985864 (TP) #

Not an insider, but I noticed that there is now a filter for using Whisper (C++) for audio transcription [1]. It looks like you provide the path to a model file [2].

[1]: https://github.com/ggml-org/whisper.cpp

[2]: https://git.ffmpeg.org/gitweb/ffmpeg.git/commit/13ce36fef98a...

replies(2): >>44986159 #>>44986233 #

3. ukuina ◴[22 Aug 25 15:59 UTC] No.44986159[source]▶

>>44985903 #

This is big news if it means realtime subtitle generation.

replies(1): >>44986222 #

4. ranger_danger ◴[22 Aug 25 16:04 UTC] No.44986222{3}[source]▶

>>44986159 #

in my experience whisper (at least on my 3070 Ti) is not capable of high quality real-time transcription. A few seconds per second of audio, maybe.

5. perihelions ◴[22 Aug 25 16:05 UTC] No.44986233[source]▶

>>44985903 #

You missed out on the thread!

https://news.ycombinator.com/item?id=44886647 ("FFmpeg 8.0 adds Whisper support (ffmpeg.org)"—9 days ago, 331 comments)

↑