https://github.com/kartikmehta8/ai-voice-to-text-transcriber-real-time
This project is a simple GUI-based application that records audio, transcribes speech using AI models from Hugging Face, and summarizes the transcribed text. The app is built using Python, PyQt6, sounddevice, and transformers.
https://github.com/kartikmehta8/ai-voice-to-text-transcriber-real-time
Last synced: 3 months ago
JSON representation
This project is a simple GUI-based application that records audio, transcribes speech using AI models from Hugging Face, and summarizes the transcribed text. The app is built using Python, PyQt6, sounddevice, and transformers.
- Host: GitHub
- URL: https://github.com/kartikmehta8/ai-voice-to-text-transcriber-real-time
- Owner: kartikmehta8
- Created: 2025-02-10T17:43:56.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-02-10T17:44:05.000Z (3 months ago)
- Last Synced: 2025-03-01T11:55:46.934Z (3 months ago)
- Language: Python
- Homepage:
- Size: 47.9 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Voice-to-Text Transcription (Local)
This project is a simple GUI-based application that records audio, transcribes speech using AI models from Hugging Face, and summarizes the transcribed text. The app is built using **Python**, **PyQt6**, **sounddevice**, and **transformers**.
## Features
**Real-time voice recording**
**AI-based transcription** using `facebook/wav2vec2-large-960h`
**AI-powered text summarization** using `facebook/bart-large-cnn`
**Simple GUI** with Start/Stop buttons using `PyQt6`
## How It Works
1. Click **Start Recording** to record your voice.
2. Click **Stop Recording** to stop and save the audio.
3. The AI will transcribe and summarize the text automatically.
4. The summarized text appears in the GUI.
## Future Enhancements
- ✅ Add support for multiple languages.
- ✅ Save transcripts to a file.
- ✅ Live streaming transcription.