Repository navigation
Add Zipformer recipe for GigaSpeech - #1254
Conversation
|
@yfyeung do you have a pretrained model you could share? |
@desh2608 Sure, check https://huggingface.co/yfyeung/icefall-asr-gigaspeech-zipformer-2023-10-17 |
|
|
||
| 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] |
There was a problem hiding this comment.
Please add a link for [Zipformer].
There was a problem hiding this comment.
OK, I removed it. It's redundant.
csukuangfj
left a comment
csukuangfj
left a comment
There was a problem hiding this comment.
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 | |||
There was a problem hiding this comment.
Is it possible to replace it with a symlnik?
There was a problem hiding this comment.
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 | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
| @@ -0,0 +1,775 @@ | |||
| #!/usr/bin/env python3 | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
| @@ -0,0 +1,522 @@ | |||
| #!/usr/bin/env python3 | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
There was a problem hiding this comment.
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) | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
| @@ -0,0 +1,436 @@ | |||
| #!/usr/bin/env python3 | |||
There was a problem hiding this comment.
can you replace it with a symlink?
| @@ -0,0 +1,273 @@ | |||
| #!/usr/bin/env python3 | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
| @@ -0,0 +1,240 @@ | |||
| #!/usr/bin/env python3 | |||
There was a problem hiding this comment.
Can you replace it with a symlink?
| - 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> |
There was a problem hiding this comment.
Could you upload the tensorboard log to
https://wandb.ai/site
and post a link to it here?
There was a problem hiding this comment.
By the way, the link has not been posted. please leave a message when you think this PR is ready to merge.
There was a problem hiding this comment.
There was a problem hiding this comment.
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> |
There was a problem hiding this comment.
Could you add a CI test for your model?
yfyeung
added
zipformer
|
Please re-review this PR. @csukuangfj |
|
I want a brand new streaming English model |
Co-authored-by: Yifan Yang <yifanyeung@qq.com> Co-authored-by: yfy62 <yfy62@d3-hpc-sjtu-test-005.cm.cluster>
Uh oh!
There was an error while loading. Please reload this page.