https://github.com/bits-by-brandon/whisper-ui

A GUI interface for Open AI Whisper based on Tauri and Sveltekit
https://github.com/bits-by-brandon/whisper-ui

rust speech-to-text svelte tauri whisper

Last synced: about 1 month ago
JSON representation

A GUI interface for Open AI Whisper based on Tauri and Sveltekit

• Host: GitHub
• URL: https://github.com/bits-by-brandon/whisper-ui
• Owner: bits-by-brandon
• Created: 2022-12-09T07:19:28.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-04-21T20:46:10.000Z (8 months ago)
• Last Synced: 2024-08-01T22:51:38.301Z (4 months ago)
• Topics: rust, speech-to-text, svelte, tauri, whisper
• Language: Svelte
• Homepage:
• Size: 24.9 MB
• Stars: 105
• Watchers: 8
• Forks: 9
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• project-awesome - bits-by-brandon/whisper-ui - A GUI interface for Open AI Whisper based on Tauri and Sveltekit (Svelte)

README

        
# Whiskey

Whiskey is a GUI for Open AI's [Whisper](https://openai.com/blog/whisper/) built using Tauri and Sveltekit.

Using cpp binaries for Whisper from [whisper.cpp](https://github.com/ggerganov/whisper.cpp)

![Screenshot of Whiskey](images/whiskey-screenshot.png)

## Features

- Transcribe audio or video files into written text

- Real-time text highlighting during playback

- Export transcriptions as .txt or .vtt files

## Planned features: 

- [x] Export files 

- [x] Rename files 

- [x] Save already opened files

- [x] Upload more than wav files

- [x] Upload video

- [x] Drag and drop

- [x] Start audio playback from line

- [ ] Record mic audio directly

- [ ] Apple Silicon, Linux, and Windows binaries

- [ ] Editable text 

- [ ] Event and errors show in UI 

- [ ] Prediction accuracy