Skip to main content

WavAutoencoder: A Self-Supervised Framework for Learning Audio Representations

Project description

WavAutoEncoder

This repository is an implementation of autoencoder based on Transformer architecture for self supervised speech representation .

Install

$ pip install wav-autoencoder

Usage

Simple example for using the model

import torch
from wav_autoencoder import WavAutoEncoderConfig ,  WavAutoEncoderModel 

>> config = WavAutoEncoderConfig()
>> model = WavAutoEncoderModel(config)
>> wav_signal = torch.randn(2, 1, 16000)
>> outputs = model(wav_signal)
>> print(outputs.shape)

Todo

Citations

@misc{
  title  = {WavAutoencoder: A Self-Supervised Framework for Learning Audio Representations},
  author = {Abdou Aziz DIOP},
  year   = {2022}
}

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

wav_autoencoder-0.0.2.tar.gz (6.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

wav_autoencoder-0.0.2-py3-none-any.whl (6.9 kB view details)

Uploaded Python 3

File details

Details for the file wav_autoencoder-0.0.2.tar.gz.

File metadata

  • Download URL: wav_autoencoder-0.0.2.tar.gz
  • Upload date:
  • Size: 6.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.9.12

File hashes

Hashes for wav_autoencoder-0.0.2.tar.gz
Algorithm Hash digest
SHA256 31f90938d70dff2bc03b2b631f5ee91f3b4b8c2aea3f20a83147a7414df6c150
MD5 38df29a7375b800fd26b03224955f8a3
BLAKE2b-256 b2244bbc15ceb8de1d33345fa5eb8f3c70f374e3dd08c6c30d6738b46d382d0f

See more details on using hashes here.

File details

Details for the file wav_autoencoder-0.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for wav_autoencoder-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 61113690f0663d619a7c0a39ae1d17ff27bd861ecd136d947c452ad6c8730076
MD5 04c0e0ce3771545509007e38c1c1810f
BLAKE2b-256 7de9a647bc59df9cf0fd254a3a6d8fafc38736cd8ba4982ffb16789b85e5d881

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page