Vincent Nguyen

Folks, did you end up findong to set up this with other models ? speechkitchen could be a solution but does not learn how to do things step by step....

By the way, is there any existing script to convert ctm files into the "kaldi training data files" text, segments, utt2spk, spk2utt ?

Are you sending sentences one by one or by batch ?

then you won't have much more throughput I think. If you want a faster system you will need to batch sentences. In my experience, for online users it does not...

update: this seems to happen only with a specific corpus. another one bigger than this works fine.

it's really weird. in the 4 files of the corpus, 1 seems to be an issue. however if I trim that file removing some "very long words" (eg words >...

is there a reason why this PR is not merged ? no improvement ?

Would there be a way, using the distillation technique, to build a single model from an ensemble ?

Jean , did you get interesting results with the multi head functionality ?

First comments: I did it on a smaller dataset (500k). If I train with multi_head 2 or 4 from the very begining, PPL explodes. If I train with Multihead 1...