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

Add Zipformer recipe for GigaSpeech #1254

Merged
merged 16 commits into from Oct 21, 2023
Merged

Add Zipformer recipe for GigaSpeech #1254

merged 16 commits into from Oct 21, 2023

Conversation

yfyeung
Copy link
Collaborator

@yfyeung yfyeung commented Sep 14, 2023

@yfyeung yfyeung changed the title Add GigaSpeech Zipformer Add Zipformer recipe for GigaSpeech Sep 15, 2023
@desh2608
Copy link
Collaborator

desh2608 commented Oct 2, 2023

@yfyeung do you have a pretrained model you could share?

@yfyeung
Copy link
Collaborator Author

yfyeung commented Oct 17, 2023

@yfyeung do you have a pretrained model you could share?

@desh2608 Sure, check https://huggingface.co/yfyeung/icefall-asr-gigaspeech-zipformer-2023-10-17

README.md Outdated
@@ -148,8 +148,11 @@ in the decoding.

### GigaSpeech

We provide two models for this recipe: [Conformer CTC model][GigaSpeech_conformer_ctc]
and [Pruned stateless RNN-T: Conformer encoder + Embedding decoder + k2 pruned RNN-T loss][GigaSpeech_pruned_transducer_stateless2].
We provide three models for this recipe: [Zipformer]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please add a link for [Zipformer].
Screenshot 2023-10-18 at 09 39 40

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK, I removed it. It's redundant.

Copy link
Collaborator

@csukuangfj csukuangfj left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

The PR gives the state-of-the-art WER for gigapseech in icefall!

Left some minor comments.

@@ -0,0 +1,444 @@
# Copyright 2021 Piotr Żelasko
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it possible to replace it with a symlnik?

Copy link
Collaborator Author

@yfyeung yfyeung Oct 18, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have modified this file. In the past, GigaSpeech XL splits need to be merged. This one uses lhotse.mux.

@@ -0,0 +1,436 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure.

@@ -0,0 +1,775 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure.

@@ -0,0 +1,522 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I changed some comments like huggingface link in it.

@@ -0,0 +1,280 @@
#!/usr/bin/env python3
# Copyright 2021-2023 Xiaomi Corporation (Author: Fangjun Kuang, Zengwei Yao)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure.

@@ -0,0 +1,436 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure

@@ -0,0 +1,273 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure.

@@ -0,0 +1,240 @@
#!/usr/bin/env python3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you replace it with a symlink?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure.

- normal-scaled model, number of model parameters: 65549011, i.e., 65.55 M

You can find a pretrained model, training logs, decoding logs, and decoding results at:
<https://huggingface.co/yfyeung/icefall-asr-gigaspeech-zipformer-2023-10-17>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you upload the tensorboard log to
https://wandb.ai/site
and post a link to it here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

By the way, the link has not been posted. please leave a message when you think this PR is ready to merge.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK, I have posted that.

- normal-scaled model, number of model parameters: 65549011, i.e., 65.55 M

You can find a pretrained model, training logs, decoding logs, and decoding results at:
<https://huggingface.co/yfyeung/icefall-asr-gigaspeech-zipformer-2023-10-17>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you add a CI test for your model?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok, I have added.

@yfyeung yfyeung added the zipformer For the upgraded zipformer recipes label Oct 20, 2023
@yfyeung yfyeung added zipformer For the upgraded zipformer recipes and removed zipformer For the upgraded zipformer recipes labels Oct 20, 2023
@yfyeung
Copy link
Collaborator Author

yfyeung commented Oct 20, 2023

Please re-review this PR. @csukuangfj

Copy link
Collaborator

@csukuangfj csukuangfj left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

@csukuangfj csukuangfj merged commit 416852e into k2-fsa:master Oct 21, 2023
36 checks passed
@yfyeung yfyeung deleted the phone2 branch October 21, 2023 12:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
zipformer For the upgraded zipformer recipes
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants