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

add RUSLAN dataset preprocessor

pull/367/head
Eren Gölge 2021-02-17 13:35:23 +00:00 committed by Eren Gölge
parent 8993120634
commit 2ca74b8ab3
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
TTS/tts/datasets/preprocess.py
View File

@ -153,7 +153,8 @@ def mailabs(root_path, meta_files=None):
def ljspeech(root_path, meta_file): def ljspeech(root_path, meta_file):
"""Normalizes the Nancy meta data file to TTS format""" """Normalizes the LJSpeech meta data file to TTS format
https://keithito.com/LJ-Speech-Dataset/"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)
items = [] items = []
speaker_name = "ljspeech" speaker_name = "ljspeech"
@ -166,6 +167,21 @@ def ljspeech(root_path, meta_file):
return items return items
def ruslan(root_path, meta_file):
"""Normalizes the RUSLAN meta data file to TTS format
https://ruslan-corpus.github.io/"""
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, 'RUSLAN', cols[0] + '.wav')
text = cols[1]
items.append([text, wav_file, speaker_name])
return items
def css10(root_path, meta_file): def css10(root_path, meta_file):
"""Normalizes the CSS10 dataset file to TTS format""" """Normalizes the CSS10 dataset file to TTS format"""
txt_file = os.path.join(root_path, meta_file) txt_file = os.path.join(root_path, meta_file)