samolubukun/Nigerian-Languages-WAZOBIA-Speech-Transcription

This Gradio application provides a user-friendly interface for transcribing spoken audio in three major Nigerian languages: Yoruba, Hausa, and Igbo. It leverages specialized Whisper and Wav2Vec2 models to convert speech to text, making it easier to process and analyze audio content in these languages. # 🎤 Nigerian Languages Speech Transcription This Gradio application provides a user-friendly interface for transcribing spoken audio in three major Nigerian languages: **Yoruba**, **Hausa**, and **Igbo**. It leverages specialized Whisper and Wav2Vec2 models to convert speech to text, making it easier to process and analyze audio content in these languages. --- ## ✨ Features * **Multi-language Support:** Transcribe audio in Yoruba, Hausa, and Igbo. * **Flexible Input:** Upload audio files (WAV, MP3, etc.) or record directly from your microphone. * **Automatic Chunking:** Handles long audio files by automatically splitting and processing them in chunks for efficient transcription. * **Real-time Feedback:** Provides transcription results quickly. * **Model Information:** Displays details about the underlying models used for each language. * **User-Friendly Interface:** Built with Gradio for an intuitive and interactive experience. --- ## 🛠️ Installation ### Prerequisites * Python 3.8+ * `pip` (Python package installer) ### Steps 1. **Clone the repository (or save `app.py` and `requirements.txt`):** ```bash git clone github.com cd Nigerian-Languages-WAZOBIA-Speech-Transcription ``` 2. **Create a virtual environment (recommended):** ```bash python -m venv venv source venv/bin/activate # On Windows, use `venv\Scripts\activate` ``` 3. **Install dependencies:** The `requirements.txt` file contains all the necessary Python packages. ```bash pip install -r requirements.txt ``` Expected content of `requirements.txt`: ``` gradio torch transformers librosa numpy ``` --- ## 🚀 Usage 1. **Run the application:** ```bash python app.py ``` 2. **Access the interface:** Once the application starts, it will provide a local URL (e.g., `127.0.0.1`). If `share=True` is enabled in `app.py`, it will also provide a public Gradio Share link. Open this URL in your web browser. 3. * …