hamos ASR Web Application

🗣️ Automatic Speech Recognition using Whisper by OpenAI ✨

Description

This web application utilizes the Whisper ASR system developed by OpenAI to perform automatic speech recognition. It allows users to upload audio files in various formats and generates transcriptions using the selected Whisper model.

Features

• Supports popular audio formats including WAV, MP3, OGG, WMA, AAC, FLAC, MP4, and FLV.
• Conversion of uploaded audio files to MP3 format for compatibility.
• Selection of different Whisper model types (Tiny, Base, Small, Medium, Large).
• Real-time transcript generation.
• Downloadable transcripts as text files.

Installation

1. Clone the repository:

   git clone https://github.com/your-username/whisper-asr-webapp.git

pip install -r requirements.txt

Usage

1.Run the application:

streamlit run app.py

2.Access the web application in your browser at http://localhost:8501.