mirror of https://github.com/coqui-ai/TTS.git
117 lines
4.4 KiB
Python
117 lines
4.4 KiB
Python
import os
|
|
import random
|
|
|
|
def tts_cache(root_path, meta_file):
|
|
"""This format is set for the meta-file generated by extract_features.py"""
|
|
txt_file = os.path.join(root_path, meta_file)
|
|
items = []
|
|
with open(txt_file, 'r', encoding='utf8') as f:
|
|
for line in f:
|
|
cols = line.split('| ')
|
|
items.append(cols) # text, wav_full_path, mel_name, linear_name, wav_len, mel_len
|
|
random.shuffle(items)
|
|
return items
|
|
|
|
|
|
def tweb(root_path, meta_file):
|
|
"""Normalize TWEB dataset.
|
|
https://www.kaggle.com/bryanpark/the-world-english-bible-speech-dataset
|
|
"""
|
|
txt_file = os.path.join(root_path, meta_file)
|
|
items = []
|
|
with open(txt_file, 'r') as ttf:
|
|
for line in ttf:
|
|
cols = line.split('\t')
|
|
wav_file = os.path.join(root_path, cols[0]+'.wav')
|
|
text = cols[1]
|
|
items.append([text, wav_file])
|
|
random.shuffle(items)
|
|
return items
|
|
|
|
|
|
# def kusal(root_path, meta_file):
|
|
# txt_file = os.path.join(root_path, meta_file)
|
|
# texts = []
|
|
# wavs = []
|
|
# with open(txt_file, "r", encoding="utf8") as f:
|
|
# frames = [
|
|
# line.split('\t') for line in f
|
|
# if line.split('\t')[0] in self.wav_files_dict.keys()
|
|
# ]
|
|
# # TODO: code the rest
|
|
# return {'text': texts, 'wavs': wavs}
|
|
|
|
|
|
def mozilla(root_path, meta_files):
|
|
"""Normalizes Mozilla meta data files to TTS format"""
|
|
import glob
|
|
meta_files = glob.glob(root_path + "/**/batch*.txt", recursive=True)
|
|
folders = [os.path.dirname(f.strip()) for f in meta_files]
|
|
items = []
|
|
for idx, meta_file in enumerate(meta_files):
|
|
folder = folders[idx]
|
|
# txt_file = os.path.join(root_path, meta_file)
|
|
txt_file = meta_file
|
|
with open(txt_file, 'r') as ttf:
|
|
for line in ttf:
|
|
cols = line.split('|')
|
|
# wav_file = os.path.join(root_path, folder, '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
|
|
random.shuffle(items)
|
|
return items
|
|
|
|
|
|
def mailabs(root_path, meta_files):
|
|
"""Normalizes M-AI-Labs meta data files to TTS format"""
|
|
folders = [os.path.dirname(f.strip()) for f in meta_files.split(",")]
|
|
meta_files = [f.strip() for f in meta_files.split(",")]
|
|
items = []
|
|
for idx, meta_file in enumerate(meta_files):
|
|
print(" | > {}".format(meta_file))
|
|
folder = folders[idx]
|
|
txt_file = os.path.join(root_path, meta_file)
|
|
with open(txt_file, 'r') as ttf:
|
|
for line in ttf:
|
|
cols = line.split('|')
|
|
wav_file = os.path.join(root_path, folder, 'wavs', cols[0]+'.wav')
|
|
if os.path.isfile(wav_file):
|
|
text = cols[1]
|
|
items.append([text, wav_file])
|
|
else:
|
|
continue
|
|
random.shuffle(items)
|
|
return items
|
|
|
|
|
|
def ljspeech(root_path, meta_file):
|
|
"""Normalizes the Nancy meta data file to TTS format"""
|
|
txt_file = os.path.join(root_path, meta_file)
|
|
items = []
|
|
with open(txt_file, 'r') as ttf:
|
|
for line in ttf:
|
|
cols = line.split('|')
|
|
wav_file = os.path.join(root_path, 'wavs', cols[0]+'.wav')
|
|
text = cols[1]
|
|
items.append([text, wav_file])
|
|
random.shuffle(items)
|
|
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)
|
|
items = []
|
|
with open(txt_file, 'r') as ttf:
|
|
for line in ttf:
|
|
id = line.split()[1]
|
|
text = line[line.find('"')+1:line.rfind('"')-1]
|
|
wav_file = root_path + 'wavn/' + id + '.wav'
|
|
items.append([text, wav_file])
|
|
random.shuffle(items)
|
|
return items |