1. Python >= 3.6
2. Clone this repository.
3. Install python requirements. Please refer requirements.txt
4. Download and extract the LJ Speech dataset. And move all wav files to LJSpeech-1.1/wavs

python train.py --config config_v1.json

To train V2 or V3 Generator, replace config_v1.json with config_v2.json or config_v3.json.
Checkpoints and copy of the configuration file are saved in cp_hifigan directory by default.
You can change the path by adding --checkpoint_path option.

Download

1. Make test_files directory and copy wav files into the directory.
2. Run the following command.

python inference.py --checkpoint_file [generator checkpoint file path]

Generated wav files are saved in generated_files by default.
You can change the path by adding --output_dir option.

1. Make test_mel_files directory and copy mel-spectrogram files into the directory.
   You can generate mel-spectrograms using Tacotron2.
2. Run the following command.

python inference_e2e.py --checkpoint_file [generator checkpoint file path]

Generated wav files are saved in generated_files_from_mel by default.
You can change the path by adding --output_dir option.