search

HawkAaron / E2E-ASR

PyTorch Implementations for End-to-End Automatic Speech Recognition
126 stars 27 forks source link

implement the ASR to TensorFlow warp binding #10

Closed zhoudoufu closed 1 year ago

zhoudoufu commented 4 years ago

@HawkAaron Hi, I am working on RNN-t training with this E2E-ASR repo, with pytorch binding. and I found you have another repo that warp MXnet and TensorFlow. I suppose that warp provides universal usage for 3 different bindings. While I do not find a plug-in place in the training code. Do I need to change pytorch method manually? What is the right way to implement ASR training with TensorFlow warp binding? Thanks in advance.

HawkAaron commented 4 years ago

You mean use tensorflow binding in this pytorch training code?

zhoudoufu commented 4 years ago

I would rewrite the training process in tensorflow, and use the tensorflow binding. I am working on this actually. Just curious, is it possible to do that (use tensorflow binding in this pytorch training code)? @HawkAaron

HawkAaron commented 4 years ago

Of course you can. Just convert pytorch tensor into tensorflow tensor, and call tensorflow rnnt loss.

manish-kumar-garg commented 4 years ago

@zhoudoufu Have a look at this issue. I think you can help.