Accessing NeMo's asr's underlying torch module

Been looking at deeppavlov as a candidate to test FGSM attack on. However, FGSM requires to differentiate the loss - Xadv=X+ϵsign(∇XJ(X,Ytrue) - and the loss is the cross-entropy between the output of the nn.module and targest.

I couldn’t find a way of accessing NeMo’s module directly nor a method activating any backward()

Any insight would be helpful :slight_smile:

Hi, @tsmendelowitz
ASR component is defined at deeppavlov.models.nemo.asr:NeMoASR, TTS component is defined at deeppavlov.models.nemo.tts:NeMoTTS.