Skip to content
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

fast-beam-search support for sherpa-onnx #347

Open
uni-manjunath-ke opened this issue Sep 26, 2023 · 7 comments
Open

fast-beam-search support for sherpa-onnx #347

uni-manjunath-ke opened this issue Sep 26, 2023 · 7 comments

Comments

@uni-manjunath-ke
Copy link

uni-manjunath-ke commented Sep 26, 2023

I found that the fast-beam-search decoding is currently not supported in sherpa-onnx. Is this activity is planned for future? If yes, when can this be expected (timeline)?

In specific, do you plan to support fast-beam-search-with-lg. Because, currently, the fast-beam-search-with-lg is not supported by zipformer/streaming-decode.py.
Thanks

@csukuangfj
Copy link
Collaborator

fast_beam_search depends on k2. If you want to use fast_beam_search, please use k2-fsa/sherap.

We are going to support HLG decoding in sherpa-onnx. If you want to use a lexicon or/and an n-gram LM in decoding, then you may find HLG decoding interesting.

Please also have a look at k2-fsa/icefall#1275

@uni-manjunath-ke
Copy link
Author

Sure, Thanks. Ya, we are interested in HLG. Hoping to see this HLG code at k2-fsa/icefall#1275 merged soon and available for usage.

@uni-manjunath-ke
Copy link
Author

Hi @csukuangfj ,
Just wanted to confirm, if the HLG code at k2-fsa/icefall#1275 is only for CTC, or it can be used with zipformers as well. Could you please confirm. Because, we are interested in Zipformer models for now.

@uni-manjunath-ke
Copy link
Author

Currently, I see in k2-fsa/icefall#1275 that HLG support is added for ICefall, When can we expect this support to be ported for sherpa-onnx? or Is that already ported to Sherpa-onnx? Thanks

@csukuangfj
Copy link
Collaborator

Currently, I see in k2-fsa/icefall#1275 that HLG support is added for ICefall, When can we expect this support to be ported for sherpa-onnx? or Is that already ported to Sherpa-onnx? Thanks

please see #349

We will finish it in two weeks.


if the HLG code at k2-fsa/icefall#1275 is only for CTC

Yes, you are right. It is only for CTC.


it can be used with zipformers as well

Zipformer is a kind of neural network, while ctc is a kind of loss function. They are two different things.
If you train a zipformer using CTC loss, then you can use HLG decoding with zipformer.
If you train a zipformer using transducer loss, then you cannot use HLG decoding with zipformer.

@csukuangfj
Copy link
Collaborator

Currently, I see in k2-fsa/icefall#1275 that HLG support is added for ICefall, When can we expect this support to be ported for sherpa-onnx? or Is that already ported to Sherpa-onnx? Thanks

@uni-manjunath-ke

#349

The C++ part is usable now.

@uni-manjunath-ke
Copy link
Author

Thank you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants