Text-to-Speech (TTS) with Transformer trained on LJSpeech

This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain using a Transformer pretrained on LJSpeech.

The pre-trained model takes in text input and produces a spectrogram in output. One can get the final waveform by applying a vocoder (e.g., HiFIGAN) on top of the generated spectrogram.

Perform Text-to-Speech (TTS)

import torchaudio
from speechbrain.inference.vocoders import HIFIGAN

texts = ["This is the example text"]

#initializing my model
my_tts_model = TextToSpeech.from_hparams(source="/content/")

#initializing vocoder(Hifigan) model
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder")

# Running the TTS
mel_output = my_tts_model.encode_text(texts)

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

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