Open LindgeW opened 11 months ago
You can refer to https://github.com/MKT-Dataoceanai/CNVSRC2023Baseline/blob/91f85db4dcb8f7036d662e1538ce7c8a9c8a7804/espnet/nets/beam_search.py#L295 for details.
Where we use weighted_scores += self.weights[k] * scores[k]
to linear combine the score of decoder and the score of ctc.
Is the one-pass decoding scheme that computes the probability of each partial hypothesis using CTC and attention model?
I don't understand what your specific problem is, can you explain it again?
Is the one-pass decoding scheme that computes the probability of each partial hypothesis using CTC and attention model?
Sure,
There are actually two decoding strategies for hybrid CTC/attention approach combining the CTC and attention-based sequence probabilities during inference, as mentioned in this original paper (https://aclanthology.org/P17-1048.pdf). Namely, rescoring and one-pass decoding. If I understand correctly, the code you provide for decoding corresponds to the one-pass decoding scheme, right?
Hi,
Could you please give the implementation details and explanation about how to decode based on the hybrid ctc/attention architecture? (how to linearly combine the ctc score and attention score to produce the final prediction when decoding?)