Prerequisites

1. Python 3.6+
2. pip to install required libraries

Required Libraries

• pytubefix: A lightweight Python library that enables the downloading of YouTube videos and the extraction of audio streams.

• whisper: An advanced speech-to-text library that facilitates accurate and efficient transcription of audio files.

• langdetect: A language detection library ported from Google's language-detection.

Installation

1. Clone this repository or download the script.

2. Install the required libraries:

   pip install pytubefix
   

   pip install git+https://github.com/openai/whisper.git
   

   pip install langdetect
   

3. Download FFmpeg and add it to environment variables.

• Windows: https://phoenixnap.com/kb/ffmpeg-windows

• Mac: https://phoenixnap.com/kb/ffmpeg-mac

• Ubuntu: https://phoenixnap.com/kb/install-ffmpeg-ubuntu

Usage

1. Run the script:

   python youtube_audio_to_text.py
   

2. When prompted, enter the YouTube video URL you wish to transcribe:

   Enter the YouTube video URL: https://www.youtube.com/watch?v=XXXXXXXXXXX
   

3. The script will download the audio, transcribe it, detect language, and save the transcription to a text file called output_{language}.txt.

4. Access the transcription by opening the output_{language}.txt file located in the same directory as the script.

Workflow

1. The user inputs a YouTube video URL when prompted.
2. The pytubefix library is used to create a YouTube object and filter the audio stream.
3. The audio stream is downloaded as an MP3 file and saved in the YoutubeAudios folder.
4. The whisper library loads a base model and transcribes the downloaded audio into text.
5. The langdetect library detects the language of the transcribed text.
6. The transcription is saved to a text file named output_{language}.txt with the language code as part of the filename and opened for the user to view.

Contributing 🤝🌱

Contributions from users are highly valued and appreciated. There are two main ways to contribute to this project: through pull requests and issues.

Pull Requests

1. Fork the repository and create a branch from the main branch.
2. Make changes or additions to the code.
3. Commit the changes, and push them to the branch.
4. Open a pull request to the main branch with a clear and concise description of the changes.

Issues

1. Navigate to the Issues section of the repository.
2. Check if there is an existing issue similar to the one you'd like to create.
3. If there isn't an existing issue, create a new issue by clicking the "New issue" button.
4. Provide a descriptive title and detailed information about the proposed changes that you want to potentially add to the current script.

🎓🌟 Feel free to contribute, share, and spread the love 💖💬🌍

This repository contains a simple yet powerful tool designed to transcribe audio files on macOS. The tool utilizes Python’s pydub and SpeechRecognition libraries to convert MP3 files into text, making it ideal for quick and efficient transcription