Vahid Noroozi

The support of Transducer models is not added to Riva yet. However you may convert these models to ONNX if you want.

You may reduce the fused_batch_size to reduce the memory consumption.

The default config is decoder.prednet.pred_hidden=640 and decoder.prednet.rnn_hidden_size=2048 which means LSTMs are going to have hidden size of 2048 with 640 projections between them to reduce the computation time. Looks like...

Hi, >> I am interested in your thoughts about the objective function, however. Is such a complicated formulation really necessary, or could you just do the dot product of the...

There was a bug that it is fixed by now. Download the code again. It should be working now. I am not sure how you have used T.ones_like, but I...

Your model file looks like to be corrupted. Please download it and try again. Even training from scratch should work. In that issue, they used a very small batch size...

I am going to try this model next week to make sure it is not a bug. Have you tried the latest nemo release or one of the old releases...

In the meantime, would you please try an older nemo version for both conversion and training?

Hi, Sorry for the late reply. I should have missed your question. I am not sure if you still have this question. Consider that in the paper they have simplified...