Closed patrickvonplaten closed 2 years ago
Might not be super important, but I was a bit surprised by the naming of the lm_score variable in https://github.com/kensho-technologies/pyctcdecode/blob/9071d5091387579b4722cfcbe0c8597ad0b16227/pyctcdecode/decoder.py#L498
lm_score
the lm_score corresponds to the normalized sum of both the logit_score and the lm_score no? See: https://github.com/kensho-technologies/pyctcdecode/blob/9071d5091387579b4722cfcbe0c8597ad0b16227/pyctcdecode/decoder.py#L326
logit_score
Shouldn't it rather be called merged_score or something?
merged_score
You're correct here. I added a small PR to clarify this.
Might not be super important, but I was a bit surprised by the naming of the
lm_score
variable in https://github.com/kensho-technologies/pyctcdecode/blob/9071d5091387579b4722cfcbe0c8597ad0b16227/pyctcdecode/decoder.py#L498the
lm_score
corresponds to the normalized sum of both thelogit_score
and thelm_score
no? See: https://github.com/kensho-technologies/pyctcdecode/blob/9071d5091387579b4722cfcbe0c8597ad0b16227/pyctcdecode/decoder.py#L326Shouldn't it rather be called
merged_score
or something?