tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Feat: add kotoba-whisper, etc

Browse Source
This commit is contained in:
litagin02
2024-05-26 22:03:19 +09:00
parent e27bd4dfbc
commit e5c189125f
7 changed files with 101 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
data_utils.py
View File

@@ -71,16 +71,16 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
self.audiopaths_sid_text, file=sys.stdout
):
audiopath = f"{_id}"
if self.min_text_len <= len(phones) and len(phones) <= self.max_text_len:
phones = phones.split(" ")
tone = [int(i) for i in tone.split(" ")]
word2ph = [int(i) for i in word2ph.split(" ")]
audiopaths_sid_text_new.append(
[audiopath, spk, language, text, phones, tone, word2ph]
)
lengths.append(os.path.getsize(audiopath) // (2 * self.hop_length))
else:
skipped += 1
# if self.min_text_len <= len(phones) and len(phones) <= self.max_text_len:
phones = phones.split(" ")
tone = [int(i) for i in tone.split(" ")]
word2ph = [int(i) for i in word2ph.split(" ")]
audiopaths_sid_text_new.append(
[audiopath, spk, language, text, phones, tone, word2ph]
)
lengths.append(os.path.getsize(audiopath) // (2 * self.hop_length))
# else:
# skipped += 1
logger.info(
"skipped: "
+ str(skipped)