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

Not using mix folder for mailabs data

pull/10/head
Thomas Werkmeister 2019-07-19 16:23:12 +02:00 committed by GitHub
parent 0470dd49f2
commit c613f8e664
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
datasets/preprocess.py
View File

@ -72,7 +72,7 @@ def mozilla(root_path, meta_file):
def mailabs(root_path, meta_files=None):
"""Normalizes M-AI-Labs meta data files to TTS format"""
speaker_regex = re.compile("by_book/(male|female|mix)/(?P<speaker_name>[^/]+)/")
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]
@ -83,7 +83,10 @@ def mailabs(root_path, meta_files=None):
items = []
for idx, csv_file in enumerate(csv_files):
# determine speaker based on folder structure...
speaker_name = speaker_regex.search(csv_file).group("speaker_name")
speaker_name_match = speaker_regex.search(csv_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)