Implementation of a HiFiGAN
See the results at the end of this README.
pip install -r ./requirements.txtTo reproduce training download LJSpeech.
sh scripts/download_data.shConfigs can be found in hw_tts/configs folder. In particular, for testing use config_server.json.
One can redefine parameters which are set within config by passing them in terminal via flags.
python train.py -c CONFIG -r CHECKPOINT -k WANDB_KEY --wandb_run_name WANDB_RUN_NAME --n_gpu NUM_GPU --batch_size BATCH_SIZE --len_epoch ITERS_PER_EPOCH --data_path PATH_TO_WAVSpython test.py -c hw_tts/configs/config_server.json -r CHECKPOINT -t test_audio -o output_audiotest_audiois a directory with 3 wavs for evaluation.output_audiois a directory to save the result.
Generation of these 3 sentences. Filename corresponds to the order of a sentence.
A defibrillator is a device that gives a high energy electric shock to the heart of someone who is in cardiac arrest
Massachusetts Institute of Technology may be best known for its math, science and engineering education
Wasserstein distance or Kantorovich Rubinstein metric is a distance function defined between probability distributions on a given metric space