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

update mozilla preprocessor

pull/10/head
Eren Golge 2019-04-28 14:05:06 +02:00
parent 70eabaf4d8
commit 278c7a91b7
1 changed files with 10 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
datasets/preprocess.py
View File

@ -41,29 +41,18 @@ def tweb(root_path, meta_file):
# return {'text': texts, 'wavs': wavs} # return {'text': texts, 'wavs': wavs}
def mozilla(root_path, meta_files): def mozilla(root_path, meta_file):
"""Normalizes Mozilla meta data files to TTS format""" """Normalizes Mozilla meta data files to TTS format"""
import glob txt_file = os.path.join(root_path, meta_file)
meta_files = glob.glob(root_path + "/**/batch*.txt", recursive=True)
folders = [os.path.dirname(f.strip()) for f in meta_files]
items = [] items = []
for idx, meta_file in enumerate(meta_files): with open(txt_file, 'r') as ttf:
folder = folders[idx] for line in ttf:
# txt_file = os.path.join(root_path, meta_file) cols = line.split('|')
txt_file = meta_file batch_no = int(cols[1].strip().split("_")[0])
with open(txt_file, 'r') as ttf: wav_folder = "batch{}".format(batch_no)
for line in ttf: wav_file = os.path.join(root_path, wav_folder, "wavs_no_processing", cols[1].strip())
cols = line.split('|') text = cols[0].strip()
# wav_file = os.path.join(root_path, folder, items.append([text, wav_file])
# 'wavs_no_processing', cols[1].strip())
wav_file = os.path.join(folder, 'wavs_no_processing',
cols[1].strip())
if os.path.isfile(wav_file):
text = cols[0].strip()
items.append([text, wav_file])
else:
print(" > Error: {}".format(wav_file))
continue
return items return items