修复有时候会出现长段无意义音频的bug #2653
Open
修复有时候会出现长段无意义音频的bug #2653
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Added logic to handle bad tokens and adjust logits based on repeated tokens during decoding.
Added logic to handle bad tokens and prevent repetition in token generation.
Owner
|
不错的建议，抽空测试下！ |
Owner
|
能否提供一些比较稳定能复现同一个token反复的case？ |
Contributor
|
大量报错,还需修改 |
Author
I'm all ears. Hmm, "拉布布" sounds a bit mysterious! |
Author
修复了一下 |
Owner
|
@jsntcheng bad_tokens_list = [809, 207,411,679,676,25,23,7]这些bad tokens是如何得到的？ |
Owner
|
0.618 1.414和35这几个值是如何考虑的？ |
Author
|
@RVC-Boss 这个修补在我们这边已经运行到现在，运行良好😄 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
生产中发现一些模型可能会因为素材或者参考音频的原因，时不时推理出大段的无意义音频，排查发现是在AR的decode阶段有点问题，进行了优化，降低了一直推出同一个token的情况。对于一些恶意token(蹩脚的叫法)，上一个修改依旧不能修复，会出现a,a,a,a,b,b,a,a,a,a这种情况，直接干掉。测试下来也没什么不妥，质量也没下降，稳定性肉眼可见的提升。人机交互产品出现那种大段的噪音真的不能接受，不是说抽卡就行的。