luganda-tts-v1

Luganda Text-to-Speech model trained with NVIDIA NeMo.

Models

• luganda_fastpitch_final.nemo - FastPitch spectrogram generator
• luganda_hifigan_final.nemo - HiFi-GAN vocoder

Usage

from nemo.collections.tts.models import FastPitchModel, HifiGanModel

# Load models
fastpitch = FastPitchModel.restore_from("luganda_fastpitch_final.nemo")
hifigan = HifiGanModel.restore_from("luganda_hifigan_final.nemo")

# Generate speech
text = "Oli otya?"
parsed = fastpitch.parse(text)
spectrogram = fastpitch.generate_spectrogram(tokens=parsed)
audio = hifigan.convert_spectrogram_to_audio(spec=spectrogram)

Training Data

Trained on Sunbird/salt Luganda studio recordings.

License

See dataset license for usage terms.