Convolutional neural networks for Google speech commands data set with PyTorch.
$ pip install -r requirements.txt
$ ./download_speech_commands_dataset.sh
$ ./train.sh
$ ./eval.sh
xuyuan and tugstugi, have participated in the Kaggle competition TensorFlow Speech Recognition Challenge and reached the 10-th place.
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