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

css10 dataset preprocessor

This commit is contained in:
Eren Gölge 2021-02-09 15:11:26 +00:00 committed by Eren Gölge
parent a2e7403ae8
commit 29d928d531
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
TTS/tts/datasets/preprocess.py
View File

@ -166,6 +166,20 @@ def ljspeech(root_path, meta_file):
return items
def css10(root_path, meta_file):
"""Normalizes the CSS10 dataset file to TTS format"""
txt_file = os.path.join(root_path, meta_file)
items = []
speaker_name = "ljspeech"
with open(txt_file, 'r') as ttf:
for line in ttf:
cols = line.split('|')
wav_file = os.path.join(root_path, cols[0])
text = cols[1]
items.append([text, wav_file, speaker_name])
return items
def nancy(root_path, meta_file):
"""Normalizes the Nancy meta data file to TTS format"""
txt_file = os.path.join(root_path, meta_file)