Text-to-Speech

Towards Fast, Controllable and Lightweight Text-to-Speech synthesis

FCL-Taco2

Block diagram of FCL-taco2, where the decoder generates mel-spectrograms in AR mode within each phoneme and is shared for all phonemes.

Training and inference scripts for FCL-taco2

Environment

  • python 3.6.10
  • torch 1.3.1
  • chainer 6.0.0
  • espnet 8.0.0
  • apex 0.1
  • numpy 1.19.1
  • kaldiio 2.15.1
  • librosa 0.8.0

Training and inference:

  • Step1. Data preparation & preprocessing

  1. Download LJSpeech

  2. Unpack downloaded LJSpeech-1.1.tar.bz2 to /xx/LJSpeech-1.1

  3. Obtain the forced alignment information by using Montreal forced aligner tool. Or you can download our alignment results, then unpack it to /xx/TextGrid

  4. Preprocess the dataset to extract mel-spectrograms, phoneme duration, pitch, energy and phoneme sequence by:

     python preprocessing.py --data-root /xx/LJSpeech-1.1 --textgrid-root /xx/TextGrid

  1. Training

     

     

     

    To finish reading, please visit source site