mirrors/DeepSpeech
2
0
Fork 0
mirror of https://github.com/mozilla/DeepSpeech.git synced 2025-10-26 11:19:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

catalan has soft-dash u"xad" char

Browse Source
This commit is contained in:
JRMeyer 2018-11-26 09:30:50 +03:00
parent efd1808128
commit 4fb68b59b4
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.compute
View File

@ -34,8 +34,8 @@
source ../tmp/venv/bin/activate
scratch=1
num_layers_dropped=0
scratch=0
num_layers_dropped=5

3
filter_train_dev_test.py
View File

@ -93,7 +93,8 @@ train_paths = locale[locale['new_bucket'] == 'train'].loc[:, ['path']]
validated_clips = pandas.read_csv('{}/{}/cv_{}_valid.csv'.format(data_dir, LOCALE, LOCALE))
validated_clips['path'] = validated_clips['wav_filename'].apply(ntpath.basename)
validated_clips['transcript'] = validated_clips['transcript'].str.replace(u'\xa0', ' ')
validated_clips['transcript'] = validated_clips['transcript'].str.replace(u'\xa0', ' ') # kyrgyz
validated_clips['transcript'] = validated_clips['transcript'].str.replace(u'\xad', ' ') # catalan