Florian Metze

Hi, absolutely, you should be able to use Eesen for handwriting recognition. The main difference between the “char” and the “phn” scripts is how the lexicon is being generated, the...

With the normal scripts, you provide the decoding script (which calls decode-faster) the model directory, the search graph directory, and the test data directory. It will compute the likelihoods using...

Hi, in most cases lattice based decoding will improve results, it gives better time alignments and allows you to specify a word insertion penalty. It will also give you word...

Kalpesh, Ramon would know best about the “v1-tf” recipe, but I can see that there is an error message that says "Can't open data/local/dict_phn/lexicon1.txt: No such file or directory at...

Good, not sure about the pickle error, but if you say it does not affect the training, then things should be fine. You should be fine running the test script...

Can you describe where exactly this occurs, specifically which branch and which script? Fundamentally, we have 46 phones, but 47 CTC outputs, because index 0 is the blank. The counts...

Which branch are you seeing this problem with?

You will need to provide 48 phones during decoding, I believe, which means 49 symbols including blank. You should be able to generate the priors using the standard call in...

Are the analyze-counts executables of Kaldi and Eesen different? All the count files that I saw from Eesen contain integer numbers, and the first number is very large, because it...

tokens.fst contains the epsilon "token" as well as the disambiguation symbols (#1, #2, ...) which you will need to insert into the FST to be able to make words unique....