|
--- |
|
language: "en" |
|
tags: |
|
- text-to-speech |
|
- TTS |
|
- speech-synthesis |
|
- Tacotron2 |
|
- speechbrain |
|
license: "apache-2.0" |
|
datasets: |
|
- LJSpeech |
|
metrics: |
|
- mos |
|
pipeline_tag: text-to-speech |
|
--- |
|
<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe> |
|
<br/><br/> |
|
|
|
# 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](https://arxiv.org/pdf/1809.08895.pdf) pretrained on [LJSpeech](https://keithito.com/LJ-Speech-Dataset/). |
|
|
|
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 |
|
``` |
|
### Perform Text-to-Speech (TTS) |
|
|
|
```python |
|
import torchaudio |
|
from TTSModel import TTSModel |
|
from speechbrain.inference.vocoders import HIFIGAN |
|
|
|
texts = ["This is a sample text for synthesis."] |
|
|
|
# Intialize TTS (Transformer) and Vocoder (HiFIGAN) |
|
my_tts_model = TTSModel.from_hparams(source="/content/") |
|
hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmpdir_vocoder") |
|
|
|
# Running the TTS |
|
mel_output, mel_length = 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) |
|
``` |
|
|
|
If you want to generate multiple sentences in one-shot, pass the sentences as items in a list. |
|
|
|
|
|
### 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: |
|
1. Clone SpeechBrain: |
|
```bash |
|
git clone https://github.com/speechbrain/speechbrain/ |
|
``` |
|
2. Install it: |
|
```bash |
|
cd speechbrain |
|
pip install -r requirements.txt |
|
pip install -e . |
|
``` |
|
3. Run Training: |
|
```bash |
|
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 |
|
``` |
|
|
|
|
|
### 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. |
|
|
|
```bibtex |
|
@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} |
|
} |
|
``` |
