Π·Π΅ΡΠΊΠ°Π»ΠΎ ΠΈΠ· https://github.com/mozilla/TTS.git
π€ π¬ Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
dataset-analysisdeep-learningganttsglow-ttsmelganmultiband-melganpythonpytorchspeaker-encoderspeechtacotrontacotron2tensorflow2text-to-speechttsvocoder
bcfd492bf0
|
||
|---|---|---|
| datasets | ||
| layers | ||
| models | ||
| png | ||
| samples | ||
| utils | ||
| .gitignore | ||
| README.md | ||
| __init__.py | ||
| config.json | ||
| module.py | ||
| requirements.txt | ||
| synthesis.py | ||
| train.py | ||
README.md
Tacotron (Work in Progress...)
Here we have pytorch implementation of: - Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model. - Tacotron2 (TODO): Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
At the end, it should be easy to add new models and try different architectures.
You can find here a brief note about possible TTS architectures and their comparisons.
Requirements
Highly recommended to use miniconda for easier installation.
- python 3.6
- pytorch > 0.2.0
- TODO
Data
TODO
File description
TODO
Training the network
TODO
Generate TTS wav file
TODO