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

sync emo branch (#159)

Browse Source 
* Update README.md

* 更新 bert_models.json

* fix

* Update data_utils.py

* Update infer.py

* performance improve

* Feat: support auto split in webui (#158)

* Feat: support auto split in webui

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

---------

Co-authored-by: Sora <atri@suzakuintsubaki.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Stardust·减
2023-11-08 17:09:15 +08:00
committed by GitHub
parent 9616b7b4b5
commit 33d153505a
7 changed files with 21 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
data_utils.py
View File

@@ -145,38 +145,24 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
word2ph[0] += 1
bert_path = wav_path.replace(".wav", ".bert.pt")
try:
bert = torch.load(bert_path)
assert bert.shape[-1] == len(phone)
bert_ori = torch.load(bert_path)
assert bert_ori.shape[-1] == len(phone)
except Exception as e:
logger.warn("Bert load Failed")
logger.warn(e)
if language_str == "ZH":
bert = bert
bert = bert_ori
ja_bert = torch.zeros(1024, len(phone))
en_bert = torch.zeros(1024, len(phone))
elif language_str == "JP":
bert = torch.zeros(1024, len(phone))
ja_bert = bert
ja_bert = bert_ori
en_bert = torch.zeros(1024, len(phone))
elif language_str == "EN":
bert = torch.zeros(1024, len(phone))
ja_bert = torch.zeros(1024, len(phone))
en_bert = bert
assert bert.shape[-1] == len(phone), (
bert.shape,
len(phone),
sum(word2ph),
p1,
p2,
t1,
t2,
pold,
pold2,
word2ph,
text,
w2pho,
)
en_bert = bert_ori
phone = torch.LongTensor(phone)
tone = torch.LongTensor(tone)
language = torch.LongTensor(language)