ggml-org/whisper.cpp

Feature request: whisper.cpp in a library (with a .Net wrapper)

Open

#303 ouverte le 21 déc. 2022

Voir sur GitHub
 (6 commentaires) (0 réactions) (0 assignés)C++ (5 535 forks)batch import
bindingshelp wanted

Métriques du dépôt

Stars
 (49 693 stars)
Métriques de merge PR
 (Merge moyen 5j 20h) (36 PRs mergées en 30 j)

Description

This is a kind of multi-application feature request.

I used whisper.cpp "through" SubtitleEdit (https://github.com/SubtitleEdit/subtitleedit).

While using SubtitleEdit/whisper.cpp, I had good results by translating subtitles individually. In short, I selected 5 or 6 subtitles and chose "translate with whisper", SubtitleEdit extracted the audio in small files (3-4 seconds each) and it was then translated by whisper.cpp. It gave good results but, right now, it's really slow because there is a big overhead of reading the 2.8G model each time.

Could a library version of "whisper.cpp" be created? The library could then be loaded in memory of SubtitleEdit (maybe with a .Net wrapper), and the model could be loaded once, and used for multiple translations.

In short, the goal is to find a way to load the model only once and be able to rapidly translate multiple small files.

Note: If I find the time, I might try to develop it myself and create a PullRequest for whisper.cpp and SubtitleEdit but I wanted to put the idea here first.

Guide contributeur