TypeError occurred when generation.

[lzswangjian]

I have followed the steps in mentioned in Read.md for generating text from src_uniq_valid.txt.
For testing, I trained a model with a small amount of annotation data.
I have rerun segmentation part and used pretrained model.
I am unable to debug it. What could be the issue?
Traceback (most recent call last):
File "chsmm.py", line 1382, in
gen_from_src()
File "chsmm.py", line 1303, in gen_from_src
gen_from_srctbl(src_tbl, top_temps, coeffs, src_line=src_line)
File "chsmm.py", line 1244, in gen_from_srctbl
str_phrases = [" ".join([str(n) if type(n) is int else n for n in phrs]) for phrs in best_phrases]
TypeError: 'NoneType' object is not iterable

[swiseman]

It looks to me like best_phrases is never getting updated, and so it remains None. This can happen, for instance, if you only generate 0-length generations.

[gwlgmz]

It looks to me like best_phrases is never getting updated, and so it remains None. This can happen, for instance, if you only generate 0-length generations.

I have the same problem and don't know how to solve it.

[SeaOfOcean]

same issue