-
Notifications
You must be signed in to change notification settings - Fork 3.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
BUG:API调用和UI使用结果不一致(发现babylon这个词无法正确生成音频) #1085
Comments
BOCEAN-FENG
changed the title
BUG:发现babylon这个词无法正确生成音频
BUG:API调用和UI使用结果不一致(发现babylon这个词无法正确生成音频)
May 13, 2024
调用的api.py还是api_v2.py? |
是api_v2.py,怎么说呀? |
seed是不是一致的? |
是一致的 我专门确认过 |
重新补充一下:发现Game mode会导致tts不断发音成‘zzzzzzzzzzzz’ |
再补充一个词:brainstorming,生成出来大概率是brainstormingzzzzzzzzzzzzzzzz这种音频 |
再补充一个词:Kabul,生成出来仍然是是带有zzzzzzzzzzzzzzzz这种音频 |
换了10个模型均无法复现 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
补充:尝试重复生成50轮同一段音频,发现音频的时长会越来越长,比如'zzzzzzz'的声音会越来越长,考虑到程序有什么内存使用问题?
fast_inferenceAPI(api_v2.py)调用,webui直接合成就没有问题,两者保持参数一致,包括种子在内
尝试过五段参考音频,包括底模在内换了三种模型,各种生成参数都调整了
发现babylon会生成babylonzzzzzzzzzzzzzzzzzzzzzzzszsz这种发音,为什么会有这种情况呢?
The text was updated successfully, but these errors were encountered: