Expressive-FastSpeech2 icon indicating copy to clipboard operation
Expressive-FastSpeech2 copied to clipboard

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

Results 7 Expressive-FastSpeech2 issues
Sort by recently updated
recently updated
newest added

When using the IEMOCAP corpus, the commands required after the execution of prepare_data.py are why

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.4.0 to 2.5.1. Release notes Sourced from tensorflow's releases. TensorFlow 2.5.1 Release 2.5.1 This release introduces several vulnerability fixes: Fixes a heap out of bounds access in...

dependencies

fix the name of _stft.stft_fn

How to get iemocap_fixed.txt and iemocap-lexicon.txt?

Could there be a package of this published to PyPI so we can `pip install` it?

I'm struggling to generate filelist.txt using the RAVDESS dataset, can you provide an example of the file? It's supposed to contain data for filelist_dict, emotion_dict, arousal_dict, valence_dict.

Hi author @keonlee9420 , Thanks for your repository, which is very useful to my project. However, I met some problem in trying to use a continuous model (following the README...