Skip to content
Snippets Groups Projects
Name Last commit Last update
src
.gitignore
LICENSE
README.md
requirements.txt

DiffWave

Note
This code is an adaptation of the original work by the LMNT team. Original repo link; version 0.17.

Part of the original README follows here:

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer. It starts with Gaussian noise and converts it into speech via iterative refinement. The speech can be controlled by providing a conditioning signal (e.g. log-scaled Mel spectrogram). The model and architecture details are described in DiffWave: A Versatile Diffusion Model for Audio Synthesis.

Pretrained models

22.05 kHz pretrained model (31 MB, SHA256: d415d2117bb0bba3999afabdd67ed11d9e43400af26193a451d112e2560821a8)

This pre-trained model is able to synthesize speech with a real-time factor of 0.87 (smaller is faster).

Pre-trained model details

  • trained on 4x 1080Ti
  • default parameters
  • single precision floating point (FP32)
  • trained on LJSpeech dataset excluding LJ001* and LJ002*
  • trained for 1000578 steps (1273 epochs)

Getting started

Using GitHub:

git clone https://gitlab.lisn.upsaclay.fr/guaranda-cabezas/diffwave
cd diffwave

Training

Before you start training, you'll need to prepare a training dataset. The dataset can have any directory structure as long as the contained .wav files are 16-bit mono (e.g. LJSpeech, VCTK). By default, this implementation assumes a sample rate of 22.05 kHz. If you need to change this value, edit params.py.

python -m diffwave.preprocess /path/to/dir/containing/wavs
python -m diffwave /path/to/model/dir /path/to/dir/containing/wavs

# in another shell to monitor training progress:
tensorboard --logdir /path/to/model/dir --bind_all

You should expect to hear intelligible (but noisy) speech by ~8k steps (~1.5h on a 2080 Ti).

Training with trajectories

You don't need to run any preprocessing.

python src/diffwave/__main__.py /path/to/model/dir /path/to/file/containing/trajectories --data_type trajectories_x # for 1D data

Multi-GPU training

By default, this implementation uses as many GPUs in parallel as returned by torch.cuda.device_count(). You can specify which GPUs to use by setting the CUDA_DEVICES_AVAILABLE environment variable before running the training module.

Inference API

Basic usage:

from diffwave.inference import predict as diffwave_predict

model_dir = '/path/to/model/dir'
spectrogram = # get your hands on a spectrogram in [N,C,W] format
audio, sample_rate = diffwave_predict(spectrogram, model_dir, fast_sampling=True)

# audio is a GPU tensor in [N,T] format.

Inference CLI

python -m diffwave.inference --fast /path/to/model /path/to/spectrogram -o output.wav

References