Subtitle composer can do that: https://subtitlecomposer.kde.org/
Also Kdenlive has a feature for it as I know, though I never tested: https://docs.kdenlive.org/en/effects_and_compositions/speech_to_text.html
this post was submitted on 06 Oct 2023
60 points (98.4% liked)
Linux
47369 readers
1187 users here now
From Wikipedia, the free encyclopedia
Linux is a family of open source Unix-like operating systems based on the Linux kernel, an operating system kernel first released on September 17, 1991 by Linus Torvalds. Linux is typically packaged in a Linux distribution (or distro for short).
Distributions include the Linux kernel and supporting system software and libraries, many of which are provided by the GNU Project. Many Linux distributions use the word "Linux" in their name, but the Free Software Foundation uses the name GNU/Linux to emphasize the importance of GNU software, causing some controversy.
Rules
- Posts must be relevant to operating systems running the Linux kernel. GNU/Linux or otherwise.
- No misinformation
- No NSFW content
- No hate speech, bigotry, etc
Related Communities
Community icon by Alpár-Etele Méder, licensed under CC BY 3.0
founded 5 years ago
MODERATORS
If you're willing to roll your own a bit, whisper.cpp is pretty good
Kdenlive apparently supports whisper. Check the link in other comment.
I'd also recommend something based on whisper.
If you're looking for live transcriptions: https://github.com/abb128/LiveCaptions
And I've fiddked around with vosk a year ago.
I wrote a TUI for whisper in bash for a journalist friend of mine for exactly this use case. It's a bit hackey, but it's a good place to start.
Whisper is your best bet for FOSS transcription. This is the most efficient implementation AFAIK: https://github.com/guillaumekln/faster-whisper.
How does whisper compare to Mozzilla's Deepspeach?
From what I've heard they're competitive for English but I've never used Deepspeech myself. Whisper has much more community support so it's probably easier to use overall.
Whisper is pretty good and open source, you just need to write your own script to do the automation.
And then you can also use some summarisation with OpenAI to create short summaries for each lecture or extract highlights or key points.
You can then upload them to Obsidian to make them indexed and searchable and can use any of their plugins to make it even better.
And you can use Syncthing to sync it to your phone.