Transcribe Video to Text

This project uses OpenAI Whisper to transcribe audio from video files into text.

🚀 Features

• Converts video speech to text automatically
• Supports multiple languages

---

📌 Prerequisites

Before running the script, ensure you have the following installed:

1️⃣ Install Python (Recommended: Python 3.11)

Mac (Using Homebrew)

brew install python@3.11
brew link --force --overwrite python@3.11

Windows/Linux

Download from: Python Official Website

Verify installation:

python3 --version

2️⃣ Install ffmpeg (Required for extracting audio from video)

Mac (Using Homebrew)

brew install ffmpeg

Windows (Using Chocolatey)

choco install ffmpeg

Linux (Ubuntu/Debian)

sudo apt update && sudo apt install ffmpeg -y

Verify installation:

ffmpeg -version

---

📥 Installation

1️⃣ Clone the Repository

git clone https://github.com/dianewalls/transcribe-app.git
cd transcribe-app

2️⃣ Create a Virtual Environment

python3 -m venv venv
source venv/bin/activate  # Mac/Linux
venv\Scripts\activate    # Windows

3️⃣ Install Dependencies

pip install --upgrade pip setuptools wheel
pip install -r requirements.txt

---

🏃 Usage

Basic Transcription (Default Whisper Model)

python transcribe_video.py path/to/video.mp4

The transcript will be saved in transcript.txt.

---

✅ Troubleshooting

1. ffmpeg: command not found

Ensure ffmpeg is installed and available in PATH. Run:

ffmpeg -version

2. python3: command not found

Ensure Python 3.11 is installed and set correctly:

python3 --version

---

📜 License

This project is open-source under the MIT License.

---

🤝 Contributing

Feel free to submit issues or pull requests!

---

📧 Contact

For any questions, reach out to dianewalls+github@gmail.com or open an issue in the repository.

Happy Transcribing! 🚀