WindyMadman/so-vits-svc
1
0
Fork 0
mirror of https://github.com/svc-develop-team/so-vits-svc.git synced 2025-01-07 03:17:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(preprocess): skip hidden files with prefix .

Browse Source
This commit is contained in:
magic-akari 2023-07-27 16:23:38 +08:00
parent a936231e9a
commit 8aeeb10c50
No known key found for this signature in database
GPG Key ID: EC005B1159285BDD
1 changed files with 21 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
preprocess_flist_config.py
View File

@ -45,32 +45,39 @@ if __name__ == "__main__":
for speaker in tqdm(os.listdir(args.source_dir)):
spk_dict[speaker] = spk_id
spk_id += 1
wavs = ["/".join([args.source_dir, speaker, i]) for i in os.listdir(os.path.join(args.source_dir, speaker))]
new_wavs = []
for file in wavs:
if not file.endswith("wav"):
wavs = []
for file_name in os.listdir(os.path.join(args.source_dir, speaker)):
if not file_name.endswith("wav"):
continue
if not pattern.match(file):
logger.warning(f"文件名{file}中包含非字母数字下划线，可能会导致错误。（也可能不会）")
if get_wav_duration(file) < 0.3:
logger.info("Skip too short audio:" + file)
if file_name.startswith("."):
continue
new_wavs.append(file)
wavs = new_wavs
file_path = "/".join([args.source_dir, speaker, file_name])
if not pattern.match(file_name):
logger.warning("Detected non-ASCII file name: " + file_path)
if get_wav_duration(file_path) < 0.3:
logger.info("Skip too short audio: " + file_path)
continue
wavs.append(file_path)
shuffle(wavs)
train += wavs[2:]
val += wavs[:2]
shuffle(train)
shuffle(val)
logger.info("Writing" + args.train_list)
logger.info("Writing " + args.train_list)
with open(args.train_list, "w") as f:
for fname in tqdm(train):
wavpath = fname
f.write(wavpath + "\n")
logger.info("Writing" + args.val_list)
logger.info("Writing " + args.val_list)
with open(args.val_list, "w") as f:
for fname in tqdm(val):
wavpath = fname