experiments
/
STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #542 from mozilla/ted-utf8-stm 

Open STM files as UTF-8
This commit is contained in:
Reuben Morais 2017-04-18 13:40:13 -03:00 committed by GitHub
parent c73d5d3f34 f5980781ef
commit 958db24232
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
util/stm.py
View File

@ -1,3 +1,4 @@
import codecs
import unicodedata import unicodedata
class STMSegment(object): class STMSegment(object):
@ -55,7 +56,7 @@ def parse_stm_file(stm_file):
Parses an STM file at ``stm_file`` into a list of :class:`STMSegment`. Parses an STM file at ``stm_file`` into a list of :class:`STMSegment`.
""" """
stm_segments = [] stm_segments = []
with open(stm_file) as stm_lines: with codecs.open(stm_file, encoding="utf-8") as stm_lines:
for stm_line in stm_lines: for stm_line in stm_lines:
stmSegment = STMSegment(stm_line) stmSegment = STMSegment(stm_line)
if not "ignore_time_segment_in_scoring" == stmSegment.transcript: if not "ignore_time_segment_in_scoring" == stmSegment.transcript: