• Stars
    star
    1,234
  • Rank 38,045 (Top 0.8 %)
  • Language Svelte
  • License
    GNU Affero Genera...
  • Created about 1 year ago
  • Updated 5 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

whishper banner

🚧 I am working on a complete rewrite of the project. Progress on this can be seen at v4 branch. Consequently, this branch will not receive any new releases or updates.

Whishper is an open-source, 100% local audio transcription and subtitling suite with a full-featured web UI.

Features

  • πŸ—£οΈ Transcribe any media to text: audio, video, etc.
    • Transcribe from URLs (any source supported by yt-dlp).
    • Upload a file to transcribe.
  • πŸ“₯ Download transcriptions in many formats: TXT, JSON, VTT, SRT or copy the raw text to your clipboard.
  • 🌐 Translate your transcriptions to any language supported by Libretranslate.
  • ✍️ Powerful subtitle editor so you don't need to leave the UI!
    • Transcription highlighting based on media position.
    • CPS (Characters per second) warnings.
    • Segment splitting.
    • Segment insertion.
    • Subtitle language selection.
  • 🏠 100% Local: transcription, translation and subtitle edition happen 100% on your machine (can even work offline!).
  • πŸš€ Fast: uses FasterWhisper as the Whisper backend: get much faster transcription times on CPU!
  • πŸ‘ Quick and easy setup: use the quick start script, or run through a few steps!
  • πŸ”₯ GPU support: use your NVIDIA GPU to get even faster transcription times!
  • 🐎 CPU support: no GPU? No problem! Whishper can run on CPU too.

Roadmap

  • Local folder as media input (#15).
  • Full-text search all transcriptions.
  • User authentication.
  • Audio recording from the browser.
  • Add insanely-fast-whisper as an optional backend (#53).
  • Support for GPU acceleration.
    • Non NVIDIA GPU support. Is it possible with faster-whisper?
  • Can we do something with seamless_communication?

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-api folder.
  • Whishper-Backend: This is the backend that coordinates frontend calls, database, and tasks. You can find it in backend folder.
  • Whishper-Frontend: This is the frontend (web UI) of the application. You can find it in frontend folder.
  • 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.

Contributing

Contributions are welcome! Feel free to open a PR with your changes, or take a look at the issues to see if there is something you can help with.

Development setup

Check out the development documentation here.

Screenshots

These screenshots are available on the official website, click any of the following links to see:

Support

Star History

Star History Chart

Credits

More Repositories

1

awesome-privacy

Awesome Privacy - A curated list of services and alternatives that respect your privacy because PRIVACY MATTERS.
12,623
star
2

Selfhosted-Google-Photos-Alternative

A complete guide on exiting Google, Amazon or any proprietary service Photos storage with all the features you would want.
166
star
3

web-whisper

OpenAI's Whisper Audio to text transcription right into your web browser! An open source AI subtitling suite.
163
star
4

blogo

A lightweight blogging engine that backs itself up to Nostr!
Go
124
star
5

kycnot

Don't get KYC'ed
Python
92
star
6

CloakMe

User-friendly Fawkes algorithm.
CSS
64
star
7

maestro

Turn natual language into commands. Your CLI tasks, now as easy as a conversation. Run it 100% offline, or use OpenAI's models.
Go
48
star
8

nerostr

nostr paid relay, but with monero
Go
32
star
9

Feetter

Create, manage and sync anonymous Nitter feeds with Feetter
Python
18
star
10

Mnemonic-Seed-Bakcup

Free templates for mnemonic seeds backup
8
star
11

openai-telegram-bot

A telegram bot to interact with ChatGPT, Dall-e and Whisper, all in the same place.
5
star
12

pluja

About me repo :D
5
star
13

crypto-knowledge

Knowledge about crypto that I have found interesting. Translations.
4
star
14

personal-website

Personal website powered by Hugo
HTML
3
star
15

stars

My stars, organized
3
star
16

rokokeys

Backup your crypto wallet mnemonic seeds in a safe way.
Python
2
star
17

Ungoogled-Chromium-Extension-Installer

A [very] simple yet effective extension installer for UnGoogled Chromium. Just an html file.
HTML
2
star
18

Flasktatic

Easy flask site to static site.
Shell
1
star
19

cryptopedia

Educational content about cryptocurrencies.
1
star