This repository showcases a classification task for Brazilian Portuguese using two model configurations: a 1D Convolutional Neural Network (CNN) combined with Long Short-Term Memory (LSTM), and a standalone 2D CNN. The CNN1D + LSTM model, based on Tostes' work, utilizes a range of frequency values from a spectrogram as input. Meanwhile, the CNN2D model processes images sized at 227x227 pixels.
Convolution 1D with LSTM
![accent](https://private-user-images.githubusercontent.com/46492977/322229278-f8a19345-4f1d-4232-a43c-84c2800d5524.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.olTzfRGjhW3dpdfTAtzu4OiwrghTAkP0tH1W6_zJqw8)
Convolution 2D
![cnn2d](https://private-user-images.githubusercontent.com/46492977/322229617-2ac9a513-25c0-4813-83e3-98e71d0807af.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.1-SMILSGqGgdZS_zLjVzDJNhGK543DQAFIvRJqGLAfs)
Two subsets of Spotify Podcasts ( Spotify A and Spotify B) more informations is presented in following repository: Spotify Subsets
- Local :
git clone https://github.com/aryamtos/accent-classification-audio.git
pip3 install -r requirements.txt
- Conda Environment 🐍
git clone https://github.com/aryamtos/accent-classification-audio.git
conda create --name myenv
conda install --file requirements.txt
conda list
docker build -t accent:2.0 .
docker images
docker run -it --gpus all --ulimit memlock=-1 --ulimit stack=67108864 -v vol/:/vol/ --name accentBr -d accent:2.0
docker exec -it accentBr /bin/bash