Tatiana Likhomanenko

Hi Martha, Please have a look at this notebook https://github.com/yandexdataschool/mlhep2015/blob/master/day2/advanced_seminars/sPlot.ipynb prepared for a summer school. There is a part called "Training on sPlot data" where you could find several approaches...

I want to reproduce in such way: I have notebook with net training and I want that notebook gives me the same results for different runnings. And one the hack...

Hi, I have measured the speed of resnet101 forward and backward, and modified resnet101 by changing a conv layer to a deformable layer. The deformable layers are used similarly to...

@juunnn, some time ago we shared the script to convert the w2l logs into tensorboard format here https://github.com/facebookresearch/wav2letter/issues/528.

cc @vineelpratap @xuqiantong

As lexicon is mapping of words into AM tokens sequence to restrict the search in the beam-search decoder, your lexicon file should contain mapping of words to the sequence of...

1) you should not deactivate wordseparator, and each underscore is a boundary between words that is why it will anyway be separate word "remarkable". You need to set its transcription...

What stride of the model did you use for phoneme and letter-based cases?

The total stride of the model is 8 which too much for letters and phonemes. ``` ... C2 1 10 21 1 2 1 -1 -1 ... C2 14 18...

The model you use is a word-piece model. Could you check if all your commands and names in the lexicon are represented as letters tokens? There could be mismatch between...