Guillaume Androz
Guillaume Androz
Hi @abhigarg-iitk I agree with you, I did not suceed to reach the same WER either even after more than 50 epochs (maybe still not fully converged). However, the difference...
Hi @abhigarg-iitk I contacted the first author of the paper and here is his answer: > Regarding the tokenizer, we use an internal word-piece model with a vocabulary of 1K....
I made a quick review of the model code and did not find any great difference with the ESPNet implementation. Maybe in the decoder... The paper refers to a single...
Also in [ESPNet](https://arxiv.org/pdf/2010.13956.pdf): >Our Conformer model consists of a Conformer encoder proposed in [7] and a Transformer decoder > In ASR tasks, the Conformer model predicts a target sequence Y...
@usimarit I'm waiting for an answer about the joint network and the choices made by the conformer team. I'll let you know when I have further details
@pourfard I could not say... I'm using the whole training dataset (960h) and after 50 epochs, the losses were 22.16 ont the training datasets and 6.3 on the dev ones....
@tund not yet, I'll try to poke him again tomorrow
I'll try to continue training for several epochs, training seems not to have ended. I'll read the paper again to look for any clue on how to reduce WER even...
I checked both files, my config file too and got the same results. So weird. I'll try to debug to find any mistake Le sam. 23 janv. 2021 13:03, Nguyễn...
I found why I always got the same test metrics.... I tested on the `test-clean` dataset and it saved a `test.tsv` file, but each time I performed another test, as...