Whishper
Whishper (formerly known as Web Whisper Plus) is a complete transcription suite. In simple words, it is a frontend for OpenAI's Whisper, but with batteries included!
Features
- Transcribe any media to text: audio, video, etc.
- Transcribe from URLs (any source supported by yt-dlp).
- Upload a file to transcribe.
- Download result in many formats: TXT, JSON, VTT, SRT or copy the raw text to your clipboard.
- Translate your transcriptions to any language supported by Libretranslate.
- Edit your subtitles in a comfy and complete web UI!
- Subtitle language selection.
- Sentence splitting.
- Large CPS (Characters per second) warnings.
- See current transcription based on media position.
- Insert new segments to the subtitles.
- Private: transcription, translation and subtitle edition happen 100% locally (can work offline!).
- Fast: uses FasterWhisper as the Whisper backend: get much faster transcription times on CPU!
- Local: transcripted files are stored locally, and you can download them!
Coming soon
- Support for GPU acceleration.
- Audio recording from the browser.
- Can we do something with seamless_communication?
Self hosting
Check out the self-hosting documentation here.
Project structure
Whishper is a collection of pieces that work together. The three main pieces are:
- Transcription-API: This is the API that enables running Faster-Whisper. You can find it in the
transcription-apifolder. - Whishper-Backend: This is the backend that coordinates frontend calls, database, and tasks. You can find it in
backendfolder. - Whishper-Frontend: This is the frontend (web UI) of the application. You can find it in
frontendfolder. - Translation (3rd party): This is the libretranslate container that is used for translating subtitles.
- MongoDB (3rd party): This is the database that stores all the information about your transcriptions.
- Nginx (3rd party): This is the proxy that allows running everything from a single domain.
Development
Check out the development documentation here.