The generated text has been truncated, with the latter part missing

[fallbernana123456]

Self Checks

• [x] This template is only for bug reports. For questions, please visit Discussions.
• [x] I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
• [x] I have searched for existing issues, including closed ones. Search issues
• [x] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• [x] Please do not modify this template and fill in all required fields.

Cloud or Self Hosted

Self Hosted (Source)

Environment Details

uv sync --python 3.12 --extra cu128

Steps to Reproduce

python fish_speech/models/text2semantic/inference.py
--text "The text you want to convert"
--prompt-text "Your reference text"
--prompt-tokens "fake.npy"
--compile

The text I generated has 1200 words, but only 782 words were generated. The generated audio is two minutes and 10 seconds. A part is missing. Why is this? There are also no excessively long error messages.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity.

[dsh54054]

same promple, When a large amount of text is used for inference, there is a probability that the problem of incomplete speech may occur earlier, with a probability of 1/50