Audio-transcriber

Simple Python audio transcriber using OpenAI's Whisper speech recognition model

Table of Contents

• Prerequisites
• Instructions

Prerequisites

Python 3.10 was used to create a virtual environment for the script to run.

Instructions

1. Create the virtual environment with python 3.10:

python3.10 -m venv .

2. Activate the virtual environment:

source bin/activate

3. Install required packages with pip

pip install -r requirements.txt

4. Run a program with Python3

4.1. For v1: python3 transcriber.py -u, --url <URL>

4.2. For v2: ./transcriber -u <url>