I am working on training/fine-tuning DeepSpeech branch/version - 0.7.0 on Linux Ubuntu 16.04 with Python version -3.6.5, TensorFlow version - 1.15.2, CUDA/cuDNN version - CUDA 10.0/cuDNN 7.6.5.
I was interested in knowing if there are any plans for implementing DeepSpeech2 based architecture with upto 3 CNN layers, 5-7 BiDirectional RNN layers with Batch Norm. Saw that this question was asked a few times here but wanted to check the current status based on the 0.7.0 branch.
Has anyone else here attempted this DeepSpeech2 model?
thanks