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

removed shuffling of data in the preprocessor, uniform indentation

This commit is contained in:
Thomas Werkmeister 2019-04-25 11:46:11 +02:00
parent 41e3e42989
commit f279fe9e8b
1 changed files with 46 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
datasets/preprocess.py
View File

@ -1,5 +1,4 @@
import os
import random
def tts_cache(root_path, meta_file):
@ -9,8 +8,8 @@ def tts_cache(root_path, meta_file):
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)
# text, wav_full_path, mel_name, linear_name, wav_len, mel_len
items.append(cols)
return items
@ -26,7 +25,6 @@ def tweb(root_path, meta_file):
wav_file = os.path.join(root_path, cols[0] + '.wav')
text = cols[1]
items.append([text, wav_file])
random.shuffle(items)
return items
@ -55,14 +53,14 @@ def mozilla(root_path, meta_files):
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(root_path, 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(cols))
continue
random.shuffle(items)
return items
@ -78,13 +76,13 @@ def mailabs(root_path, meta_files):
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')
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
@ -98,7 +96,6 @@ def ljspeech(root_path, meta_file):
wav_file = os.path.join(root_path, 'wavs', cols[0] + '.wav')
text = cols[1]
items.append([text, wav_file])
random.shuffle(items)
return items
@ -112,7 +109,6 @@ def nancy(root_path, meta_file):
text = line[line.find('"') + 1:line.rfind('"') - 1]
wav_file = os.path.join(root_path, "wavn", id + ".wav")
items.append([text, wav_file])
random.shuffle(items)
return items
@ -126,7 +122,6 @@ def common_voice(root_path, meta_file):
continue
cols = line.split("\t")
text = cols[2]
# Files need to be first converted to wav...
wav_file = os.path.join(root_path, "clips", cols[1] + ".wav")
items.append([text, wav_file])
return items