A package for training audio denoisers
Project description
Denoisers
Denoisers is a denoising library for audio with a focus on simplicity and ease of use. There are two major types of architectures available. WaveUNet for waveform denoising and UNet for spectrogram denoising.
Usage/Examples
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)
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].cuda()
with torch.no_grad():
clean_chunk = model(audio_chunk[None])
clean.append(clean_chunk.squeeze(0).cpu())
denoised = torch.concat(clean)[:, :audio.shape[-1]]
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
denoisers-0.1.0.tar.gz
(18.3 kB
view hashes)
Built Distribution
denoisers-0.1.0-py3-none-any.whl
(22.9 kB
view hashes)
Close
Hashes for denoisers-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7331f016329c06690d7368aa3ecf1756f893bd33c8f049b3777456d9cc0eec57 |
|
MD5 | d8bbab4a49841a3180e73917513ce602 |
|
BLAKE2b-256 | af2452598e469fe9ded35eb83423505152f097846e8f1f085c6b339713f0ab5a |