Thanks to StyleSpeech, we built up our codes based on Link

0. LibriTTS dataset (train-clean-100 and train-clean-360) is used.
1. Sampling rate is set to 16000Hz.
2. This is the implementation of SC-StyleSpeech.
   For SC-TransferTTS, please refer to the branch SC-TransferTTS

• Demo page

• Clone this repository.
• Install python requirements. Please refer requirements.txt

0. Run

python prepare_align.py --data_path [LibriTTS DATAPATH]

for some preparations.

1. Montreal Forced Aligner (MFA) is used to obtain the alignments between the utterances and the phoneme sequences. 1-1. Download MFA following the command in the website. 1-2. Run the below codes

$ conda activate aligner
$ mfa model download acoustic english_mfa
$ mfa align ......LibriTTS/wav16 lexicon.txt english_us_arpa .........LibriTTS/Textgrid

2. Run

python preprocess.py

2-0. Check input&output data paths.

python train.py

0. Change default settings --data_path [Preprocessed LibriTTS DATAPATH] --save_path [Experiment SAVEPATH]
1. You can change hyperparameters of SC-CNN (kernel_size, channels), or other model configurations in configs/config.json

0. Mel generation

python synthesize.py --checkpoint_path [CKPT PATH] --ref_audio [REF AUDIO PATH] --text [INPUT TEXT]