Kinyarwandatts Female Voice

🚀 Kinyarwanda Text-to-Speech Model

An end-to-end deep-learning-based Kinyarwanda Text-to-Speech (TTS) model.

🚀 Quick Start

This model is an end-to-end deep-learning-based Kinyarwanda Text-to-Speech (TTS). It was trained using the Coqui's TTS library and the YourTTS[1] architecture.

📦 Installation

1. Install the Coqui's TTS library:

pip install TTS

2. Download the files from this repo, then run:

tts --text "text" --model_path model.pth --config_path config.json --speakers_file_path speakers.pth --speaker_wav conditioning_audio.wav --out_path out.wav

Note: The conditioning audio is a wav file(s) to condition a multi-speaker TTS model with a Speaker Encoder. You can give multiple file paths, and the d_vectors is computed as their average.

💻 Usage Examples

Basic Usage

# Install the Coqui's TTS library
pip install TTS

# Run the TTS command
tts --text "text" --model_path model.pth --config_path config.json --speakers_file_path speakers.pth --speaker_wav conditioning_audio.wav --out_path out.wav

📚 Documentation

Model Information

📄 License

This model is licensed under the cc-by-sa-4.0 license.

📖 References

[1] YourTTS paper

[2] Kinyarwanda TTS: Using a multi-speaker dataset to build a Kinyarwanda TTS model