Toggle navigation
Toggle navigation
此项目
正在载入...
Sign in
xuning
/
sherpaonnx
转到一个项目
Toggle navigation
项目
群组
代码片段
帮助
Toggle navigation pinning
Project
Activity
Repository
Pipelines
Graphs
Issues
0
Merge Requests
0
Wiki
Network
Create a new issue
Builds
Commits
Authored by
ahadjawaid
2025-02-02 23:49:42 -0600
Browse Files
Options
Browse Files
Download
Email Patches
Plain Diff
Committed by
GitHub
2025-02-03 13:49:42 +0800
Commit
8677d83efce8a1eddb626280b1c3cd63469fd0dc
8677d83e
1 parent
1d950a88
Fix: Prepend 0 to tokenization to prevent word skipping for Kokoro. (#1787)
Addressed issue Skipping words #1777
隐藏空白字符变更
内嵌
并排对比
正在显示
1 个修改的文件
包含
2 行增加
和
0 行删除
sherpa-onnx/csrc/piper-phonemize-lexicon.cc
sherpa-onnx/csrc/piper-phonemize-lexicon.cc
查看文件 @
8677d83
...
...
@@ -163,6 +163,8 @@ static std::vector<std::vector<int64_t>> PiperPhonemesToIdsKokoro(
std
::
vector
<
int64_t
>
current
;
current
.
reserve
(
phonemes
.
size
());
current
.
push_back
(
0
);
for
(
auto
p
:
phonemes
)
{
if
(
token2id
.
count
(
p
))
{
if
(
current
.
size
()
>
max_len
-
1
)
{
...
...
请
注册
或
登录
后发表评论