coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #243 from twerkmeister/patch-6 

root path speaker matching
pull/10/head
Eren Gölge 2019-07-24 11:53:09 +02:00 committed by GitHub
parent b1657d70b1 468abc0872
commit a77baefbeb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
datasets/preprocess.py
View File

@ -75,21 +75,19 @@ def mailabs(root_path, meta_files=None):
speaker_regex = re.compile("by_book/(male|female)/(?P<speaker_name>[^/]+)/")
if meta_files is None:
csv_files = glob(root_path+"/**/metadata.csv", recursive=True)
folders = [os.path.dirname(f) for f in csv_files]
else:
csv_files = meta_files
folders = [f.strip().split("by_book")[1][1:] for f in csv_files]
# meta_files = [f.strip() for f in meta_files.split(",")]
items = []
for idx, csv_file in enumerate(csv_files):
for csv_file in csv_files:
txt_file = os.path.join(root_path, csv_file)
folder = os.path.dirname(txt_file)
# determine speaker based on folder structure...
speaker_name_match = speaker_regex.search(csv_file)
speaker_name_match = speaker_regex.search(txt_file)
if speaker_name_match is None:
continue
speaker_name = speaker_name_match.group("speaker_name")
print(" | > {}".format(csv_file))
folder = folders[idx]
txt_file = os.path.join(root_path, csv_file)
with open(txt_file, 'r') as ttf:
for line in ttf:
cols = line.split('|')