nurtas-m

Hello, @ellurunaresh No, we did not include the stopping criteria still.

1) All of the training log details printed by tensor2tensor's transformer model. So, I think you may search the explanations of the logs in [tensor2tensor](https://github.com/tensorflow/tensor2tensor) project. 2) Please, clone the...

Hello, @prashantserai Can you, please, install tensor2tensor ver=1.5.7? Current version of g2p-seq2seq is incompatible with tensor2tensor=>1.6.0

Hello, @prashantserai Can you, please, print out new error message? I want to be sure that g2p-seq2seq calls the right version of tensor2tensor.

Yes, we wish to fix this problem. The problem arises because we want iteratively call the decode_word() method and transmit to it the initial word. But, in tensor2tesnor implementation of...

Fixed with commit: a1e5722bf5545beae3f7051623ca03f5b7a89793

Our program work with the ordinary tensorflow too, not only tensorflow-gpu. In case when you run this toolkit on the machine without gpu, please, change install requires in setup.py file...

Currently we working on the issue of launching our program with the new tensor2tensor and tensorflow versions. Sorry, there are a lot of changes were implemented in new tensor2tensor. We...

Hello, @michem32 Today we implemented new version of g2p-seq2seq that should be compatible with new tensor2tensor=1.5.7

In my opinion, you still have the old version of g2p-seq2seq: `File "/usr/local/bin/g2p-seq2seq", line 11, in load_entry_point('g2p-seq2seq==5.0.0a0', 'console_scripts', 'g2p-seq2seq')()`