[paraformer] support chunk mask #2282
Merged
+216
−95
Conversation
This file contains 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
重构encoder 支持wenet/transformer/encoder's dynamic chunk training
QA
0 为什么要支持paraformer mask training？
尝试使用pretrain的非流paraformer，fintune训练u2++ like的流式模型，看是否可以得到好的效果
1 为什么要有：IdentitySubsampling？
因为wenet顺序是： cmvn->subsampling->pos emb
paraformer 顺序是： lfr(subsampling) ->cmvn -> pos_emb
所以这里实现了个IdentitySubsampling， 什么也不做,只是调用了pos emb class，保持接口不变
2 paraformer fsm block中有padding， 可能对流式训练有影响（训练和推理chunk不一致）
TODO
example:
ctc_weight: 0.3
use_dynamic_chunk: true
Next PR