🎯 Bangla Speech-to-TextMade Simple

Professional-grade Bangla speech recognition powered by OpenAI Whisper. Convert your Bangla audio files to text with high accuracy and blazing speed.

✨ Powerful Features

🇧🇩 Bangla Optimized
Specifically designed and optimized for Bangla language speech recognition with superior accuracy.
⚡ Lightning Fast
Multiple model sizes from tiny (39MB) to large (1.5GB) for different speed and accuracy needs.
🖥️ Cross-Platform
Works seamlessly on Windows, macOS, and Linux with automatic FFmpeg setup.
🎵 Multiple Formats
Supports MP3, WAV, M4A, MP4, WebM, and many more audio/video formats.
💾 Easy Output
Save transcriptions to text files with simple command-line options.
🛡️ Robust
Comprehensive error handling and validation for smooth user experience.

🚀 Quick Start

Installation

pip install -r requirements.txt

Install all dependencies including OpenAI Whisper, PyTorch, and FFmpeg.

Usage

python transcribe.py audio.mp3

Simple one-command transcription with automatic model selection.

🎯 Available Models

tiny
39 MB

⚡ Fastest

Good
base
74 MB

⚡ Fast

Better
small
244 MB

🟡 Medium

Great
medium
769 MB

🟡 Slow

Excellent
large
1.5 GB

🔴 Slowest

Best

🤝 Support the Project

Built with ❤️ for the Bangla community. Your support helps make speech recognition technology more accessible to 230+ million Bangla speakers worldwide.