berab / pytorch-speech-commands

smae here

Convolutional neural networks for Google speech commands data set with PyTorch.

First to do

$ pip install -r requirements.txt
$ ./download_speech_commands_dataset.sh

Training and evaluation

$ ./train.sh
$ ./eval.sh

General

xuyuan and tugstugi, have participated in the Kaggle competition TensorFlow Speech Recognition Challenge and reached the 10-th place.

Features

• 1x32x32 mel-spectrogram as network input
• single network implementation both for CIFAR10 and Google speech commands data sets
• faster audio data augmentation on STFT
• Kaggle private LB scores evaluated on 150.000+ audio files