https://github.com/will-rice/denoisers

Simple PyTorch Denoisers for Waveform Audio
https://github.com/will-rice/denoisers

audio audio-denoising denoiser denoisers denoising pytorch pytorch-lightning speech-enhancement unet waveunet

Last synced: about 2 months ago
JSON representation

Simple PyTorch Denoisers for Waveform Audio

• Host: GitHub
• URL: https://github.com/will-rice/denoisers
• Owner: will-rice
• License: apache-2.0
• Created: 2022-09-27T20:32:10.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-11T16:41:35.000Z (4 months ago)
• Last Synced: 2024-07-08T03:33:22.823Z (3 months ago)
• Topics: audio, audio-denoising, denoiser, denoisers, denoising, pytorch, pytorch-lightning, speech-enhancement, unet, waveunet
• Language: Python
• Homepage:
• Size: 107 KB
• Stars: 28
• Watchers: 4
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Denoisers

Denoisers is a denoising library for audio with a focus on simplicity and ease of use. There are two major architectures available for waveforms: WaveUNet which follows the [paper](https://arxiv.org/abs/1806.03185) and a custom UNet1D architecture similar to what you would see in diffusion models.

## Demo

[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/wrice/denoisers)

## Usage/Examples

```sh

pip install denoisers

```

```python

import torch

import torchaudio

from denoisers import WaveUNetModel

from tqdm import tqdm

model = WaveUNetModel.from_pretrained("wrice/waveunet-vctk-24khz")

audio, sr = torchaudio.load("noisy_audio.wav")

if sr != model.config.sample_rate:

    audio = torchaudio.functional.resample(audio, sr, model.config.sample_rate)

if audio.size(0) > 1:

    audio = audio.mean(0, keepdim=True)

chunk_size = model.config.max_length

padding = abs(audio.size(-1) % chunk_size - chunk_size)

padded = torch.nn.functional.pad(audio, (0, padding))

clean = []

for i in tqdm(range(0, padded.shape[-1], chunk_size)):

    audio_chunk = padded[:, i:i + chunk_size]

    with torch.no_grad():

        clean_chunk = model(audio_chunk[None]).audio

    clean.append(clean_chunk.squeeze(0))

denoised = torch.concat(clean, 1)[:, :audio.shape[-1]]

```