Text-to-Speech (TTS) with Tacotron2 trained on LJSpeech

This repository provides all the necessary tools for Text-to-Speech (TTS) with SpeechBrain using a Tacotron2 pretrained on ALLFA Public.

The pre-trained model takes in input a short text 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.

Install SpeechBrain

pip install speechbrain

Please notice that we encourage you to read the tutorials and learn more about SpeechBrain.

Perform Text-to-Speech (TTS)

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

# Intialize TTS (tacotron2) and Vocoder (HiFIGAN)
tacotron2 = Tacotron2.from_hparams(source="aioxlabs/tacotron-swahili", savedir="tmpdir_tts")
hifi_gan = HIFIGAN.from_hparams(source="aioxlabs/hifigan-swahili", savedir="tmpdir_vocoder")

# Running the TTS
mel_output, mel_length, alignment = tacotron2.encode_text("raisi wa jumhuri ya tanzania")

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

# Save the waverform
torchaudio.save('example_TTS.wav',waveforms.squeeze(1), 16000)

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="aioxlabs/tacotron-swahili", savedir="tmpdir")
items = [
       "raisi wa jumhuri ya tanzania",
       "soma zaidi"
     ]
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.

Training

The model was trained with SpeechBrain. To train it from scratch follow these steps:

Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

Run Training:

cd recipes/LJSpeech/TTS/tacotron2/
python train.py --device=cuda:0 --max_grad_norm=1.0 --data_folder=/your_folder/LJSpeech-1.1 hparams/train.yaml

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

About SpeechBrain

Website: https://speechbrain.github.io/
Code: https://github.com/speechbrain/speechbrain/
HuggingFace: https://huggingface.co/speechbrain/

Citing SpeechBrain

Please, cite SpeechBrain if you use it for your research or business.

@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}