This repo contains the training code for Phoneme-level ASR for Voice Conversion (VC) and TTS (Text-Mel Alignment) used in StarGANv2-VC and StyleTTS.


  1. Python >= 3.7
  2. Clone this repository:

cd AuxiliaryASR
  1. Install python requirements:
pip install SoundFile torchaudio torch jiwer pyyaml click matplotlib g2p_en
  1. Prepare your own dataset and put the train_list.txt and val_list.txt in the Data folder (see Training section for more details).


python --config_path ./Configs/config.yml

Please specify the training and validation data in config.yml file. The data list format needs to be filename.wav|label|speaker_number, see train_list.txt as an example (a subset for LJSpeech). Note that speaker_number can just be 0 for ASR, but it is useful to set a meaningful number for TTS training (if you need to use this repo for StyleTTS).

Checkpoints and Tensorboard logs will be saved at log_dir. To speed up training, you may want to make batch_size as large as your GPU RAM can take. However, please note that batch_size = 64 will take around 10G GPU RAM.


This repo is set up for English with the g2p_en package, but you can train it with other languages. If you would like to train for datasets in different languages, you will need to modify the file (L86-93) with your own phonemizer. You also need to change the vocabulary file (word_index_dict.txt) and change n_token in config.yml to reflect the number of tokens. A recommended phonemizer for other languages is phonemizer.



The author would like to thank @tosaka-m for his great repository and valuable discussions.


View Github