Tts Tacotron2 Lug

🚀 Sunbird AI Text-to-Speech (TTS) model trained on Luganda text

This project offers a Text-to-Speech (TTS) solution using Tacotron2, trained on professional studio recordings, enabling the conversion of Luganda text into natural-sounding speech.

✨ Features

• Text-to-Speech (TTS): The pre - trained model can convert short Luganda text into spectrograms, and with a vocoder, it can generate the final waveform.
• Batch Processing: Capable of generating multiple sentences in one - shot.
• GPU Inference: Supports inference on the GPU for faster processing.

📦 Installation

Install SpeechBrain

pip install speechbrain

💻 Usage Examples

Basic Usage

import torchaudio
from speechbrain.pretrained import Tacotron2
from speechbrain.pretrained import HIFIGAN

# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
tacotron2 = Tacotron2.from_hparams(source="/Sunbird/sunbird-lug-tts", savedir="tmpdir_tts")
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")

# Running the TTS
mel_output, mel_length, alignment = tacotron2.encode_text("Mbagaliza Christmass Enungi Nomwaka Omugya Gubaberere Gwamirembe")

# Running Vocoder (spectrogram-to-waveform)
waveforms = hifi_gan.decode_batch(mel_output)

# Save the waverform
torchaudio.save('example_TTS.wav',waveforms.squeeze(1), 22050)

Advanced Usage

If you want to generate multiple sentences in one - shot, you can do in this way:

from speechbrain.pretrained import Tacotron2
tacotron2 = Tacotron2.from_hparams(source="speechbrain/TTS_Tacotron2", savedir="tmpdir")

items = [
       "Nsanyuse okukulaba",
       "Erinnya lyo ggwe ani?",
       "Mbagaliza Christmass Enungi Nomwaka Omugya Gubaberere Gwamirembe"
     ]
mel_outputs, mel_lengths, alignments = tacotron2.encode_batch(items)

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

📄 License

This project is licensed under the apache - 2.0 license.