Tatiana Likhomanenko

> Is it possible to use StreamingTDSModelConverter.cpp to serialize SOTA/2019 models for inference ? It only support for now TDS CTC models, so you can use our sota TDS model...

@Bernardo-Favoreto, you are always welcome to ask questions! 1, 2) yes, whatever order of words can be in lexicon, just preserve order of nbest wp splits for a particular word...

When you fork it means you don't use optimizer state and just initialize network with previously trained model. So you don't need warmup, you continue training. The difference with continue...

Nice, what was the error that you report before that the model doesn't converge? How did you solve it?

`--lrcrit` is for criterion which could have also trained params, like for ASG it is transition matrix, and for s2s models it ise AM-decoder, so for ctc this param is...

Sorry for delay, > So If I understand correctly, If I want to use a token level LM, then I need to train a token level AM as well ?...

Yep, correct! for LM training don't use dev/test sets from AM data (you can use train transcriptions, otherwise you will over-fit and cannot notice/measure it).

Your loss is going down, just very slowly. Try to increase learning rate, say try 1.0 and 2.0

First, there is no any restrictions that lr should be [0, 1]. Second with lr = 1 and lr = 2 in your log loss actually doesn't decrease, which means...

Hi @samin9796, > 1. I want to build a character level LM. Previously I built a word level LM using KENLM and for that I created a text file with...