UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

This is an unofficial PyTorch implementation of Jang et al. (Kakao), UnivNet.

To-Do List

  • [ ] Release checkpoint of pre-trained model
  • [ ] Extract wav samples for audio sample page
  • [ ] Add results including validation loss graph

Key Features

  • According to the authors of the paper, UnivNet obtained the best objective results among the recent GAN-based neural vocoders (including HiFi-GAN) as well as outperforming HiFi-GAN in a subjective evaluation. Also its inference speed is 1.5 times faster than HiFi-GAN.

  • This repository uses the same mel-spectrogram function as the Official HiFi-GAN, which is compatible with NVIDIA/tacotron2.

  • Our default mel calculation hyperparameters are as below, following the original paper.

      n_mel_channels: 100
      filter_length: 1024
      hop_length: 256 # WARNING: this can't be changed.
      win_length: 1024
      sampling_rate: 24000
      mel_fmin: 0.0
      mel_fmax: 12000.0

    You can modify the hyperparameters to be compatible with your acoustic model.


The implementation needs following dependencies.

  1. Python 3.6
  2. PyTorch 1.6.0
  3. NumPy 1.17.4 and SciPy 1.5.4
  4. Install other dependencies in requirements.txt.
    pip install -r requirements.txt


Preparing Data

  • Download the training dataset. This can be any wav file with sampling rate 24,000Hz. The original paper used LibriTTS.
    • LibriTTS train-clean-360 split tar.gz link
    • Unzip and place its contents under datasets/LibriTTS/train-clean-360.
  • If you want to use wav files with a different sampling rate, please edit the configuration file (see below).

Note: The mel-spectrograms calculated from audio file will be saved as **.mel at first, and then loaded from disk afterwards.

Preparing Metadata

Following the format from NVIDIA/tacotron2, the metadata should be formatted as:


Train/validation metadata for LibriTTS train-clean-360 split and are already prepared in datasets/metadata.
5% of the train-clean-360 utterances were randomly sampled for validation.

Since this model is a vocoder, the transcripts are NOT used during training.


Preparing Configuration Files

  • Run cp config/default.yaml config/config.yaml and then edit config.yaml

  • Write down the root path of train/validation in the data section. The data loader parses list of files within the path recursively.

      train_dir: 'datasets/'	# root path of train data (either relative/absoulte path is ok)
      train_meta: 'metadata/libritts_train_clean_360_train.txt'	# relative path of metadata file from train_dir
      val_dir: 'datasets/'		# root path of validation data
      val_meta: 'metadata/libritts_train_clean_360_val.txt'		# relative path of metadata file from val_dir

    We provide the default metadata for LibriTTS train-clean-360 split.

  • Modify channel_size in gen to switch between UnivNet-c16 and c32.

      noise_dim: 64
      channel_size: 32 # 32 or 16
      dilations: [1, 3, 9, 27]
      strides: [8, 8, 4]
      lReLU_slope: 0.2


python trainer.py -c CONFIG_YAML_FILE -n NAME_OF_THE_RUN


tensorboard --logdir logs/

If you are running tensorboard on a remote machine, you can open the tensorboard page by adding --bind_all option.


python inference.py -p CHECKPOINT_PATH -i INPUT_MEL_PATH

Pre-trained Model

A pre-trained model will be released soon.
The model was trained on LibriTTS train-clean-360 split.


See audio samples at https://mindslab-ai.github.io/univnet/

Comparison with the results on paper

Model MOS PESQ(↑) RMSE(↓)
Recordings 4.16±0.09 4.50 0.000
Results in Paper (UnivNet-c32) 3.93±0.09 3.70 0.316
Ours (UnivNet-c32) - TBD TBD


This code is an unofficial implementation, there may be some differences from the original paper.

  • Our UnivNet generator has smaller number of parameters (c32: 5.11M, c16: 1.42M) than the paper (c32: 14.89M, c16: 4.00M). So far, we have not encountered any issues from using a smaller model size. If run into any problem, please report it as an issue.

Implementation Authors

Implementation authors are: