Where are the pre-trained models? It's worthless without them. Edit: NM, someone hunted down the AWS links

    wget https://s3.amazonaws.com/wav2letter/models/librispeech-glu-highdropout.bin

    wget https://s3.amazonaws.com/wav2letter/models/librispeech-glu-highdropout-cpu.bin

    wget https://s3.amazonaws.com/wav2letter/models/librispeech-glu-lowdropout.bin