You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
when alpha is set to 0.0 or lm_path is None, there is no problem with beam_scores . I mean the best index is 0 and the corresponding beamscore is the lowest.
I want to know whether the beam_scores only represent the pure prefix ctc beam score?
How can i get the sorted beam_scores with lm-decoding?
By the way, The same problem esxits when decoding real logits(not rand). Some of the scores are normal but some are very large.
The vocabulary(labels) is as follow:
The test code in as follow:
when
alpha
is set to 0.0 orlm_path
is None, there is no problem withbeam_scores
. I mean the best index is 0 and the corresponding beamscore is the lowest.but when
alpha
is 0.3, It looks like that thebeam_scores
hasn't been sorted.I want to know whether the
beam_scores
only represent the pure prefix ctc beam score?How can i get the sorted beam_scores with lm-decoding?
By the way, The same problem esxits when decoding real logits(not rand). Some of the scores are normal but some are very large.
The vocabulary(labels) is as follow:
Hope someone can help me~
The text was updated successfully, but these errors were encountered: