tensorflow_end2end_speech_recognition icon indicating copy to clipboard operation
tensorflow_end2end_speech_recognition copied to clipboard

Published 20 hours ago • verified publisher icon hirofumi0810

models/attention/decoders/attention_layer.py

Open cuhkebook opened this issue 7 years ago • 1 comments

In the class AttentionLayer (models/attention/decoders/attention_layer.py), the initial parameter does not include "sigmoid_smoothing".

But, in models/attention/attention_seq2seq.py, it calls AttentionLayer with sigmoid_smoothing=self.sigmoid_smoothing (line 338).

Which file should I modify? Thx!

cuhkebook avatar Oct 26 '17 02:10 cuhkebook

Encountered the same problem too. So what did you do? I added an parameter "sigmoid_smoothing", and assigned default value to it, will it be ok?

CyanHillFox avatar Dec 07 '17 13:12 CyanHillFox