For a general PyTorch model you could use forward hooks to get the intermediate activations as described here. Since NeMo seems to be using a PyTorch model internally, you would have to access its layers to register the hooks.
For a general PyTorch model you could use forward hooks to get the intermediate activations as described here. Since NeMo seems to be using a PyTorch model internally, you would have to access its layers to register the hooks.