This repository is an implementation of masked wavautoencoder based on Transformer architecture for self supervised speech representation .
$ pip install wav-autoencoderSimple 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)@misc{
title = {WavAutoencoder: A Self-Supervised Framework for Learning Audio Representations},
author = {Abdou Aziz DIOP},
year = {2022}
}