File size: 2,916 Bytes
8a1292d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
# coding=gbk
import os
import argparse
import librosa
import numpy as np
from multiprocessing import Pool, cpu_count
import soundfile
from scipy.io import wavfile
from tqdm import tqdm
global speaker_annos
speaker_annos = []
def process(item):
spkdir, wav_name, args = item
speaker = spkdir.replace("\\", "/").split("/")[-1]
wav_path = os.path.join(args.in_dir, speaker, wav_name)
if os.path.exists(wav_path) and '.wav' in wav_path:
os.makedirs(os.path.join(args.out_dir, speaker), exist_ok=True)
wav, sr = librosa.load(wav_path, sr=args.sr)
soundfile.write(
os.path.join(args.out_dir, speaker, wav_name),
wav,
sr
)
def process_text(item):
spkdir, wav_name, args = item
speaker = spkdir.replace("\\", "/").split("/")[-1]
wav_path = os.path.join(args.in_dir, speaker, wav_name)
global speaker_annos
tr_name = wav_name.replace('.wav', '')
with open(args.out_dir+'/'+speaker+'/'+tr_name+'.lab', "r", encoding="utf-8") as file:
text = file.read()
text = text.replace("{NICKNAME}",'������')
text = text.replace("{M#��}{F#��}",'��')
text = text.replace("{M#��}{F#��}",'��')
substring = "{M#����}{F#���}"
if substring in text:
if tr_name.endswith("a"):
text = text.replace("{M#����}{F#���}",'����')
if tr_name.endswith("b"):
text = text.replace("{M#����}{F#���}",'���')
text = text.replace("#",'')
text = "ZH|" + text + "\n" #
speaker_annos.append(args.out_dir+'/'+speaker+'/'+wav_name+ "|" + speaker + "|" + text)
if __name__ == "__main__":
parent_dir = "./genshin_dataset/"
speaker_names = list(os.walk(parent_dir))[0][1]
parser = argparse.ArgumentParser()
parser.add_argument("--sr", type=int, default=44100, help="sampling rate")
parser.add_argument("--in_dir", type=str, default="./genshin_dataset", help="path to source dir")
parser.add_argument("--out_dir", type=str, default="./genshin_dataset", help="path to target dir")
args = parser.parse_args()
# processs = 8
processs = cpu_count()-2 if cpu_count() >4 else 1
pool = Pool(processes=processs)
for speaker in os.listdir(args.in_dir):
spk_dir = os.path.join(args.in_dir, speaker)
if os.path.isdir(spk_dir):
print(spk_dir)
for _ in tqdm(pool.imap_unordered(process, [(spk_dir, i, args) for i in os.listdir(spk_dir) if i.endswith("wav")])):
pass
for i in os.listdir(spk_dir):
if i.endswith("wav"):
pro=(spk_dir, i, args)
process_text(pro)
if len(speaker_annos) == 0:
print("transcribe error!!!")
with open("./filelists/short_character_anno.list", 'w', encoding='utf-8') as f:
for line in speaker_annos:
f.write(line)
print("transcript file finished.")
|