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Outdated suggestions cannot be applied.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.
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
Attention encoder-decoder models for multiple speech-to-text tasks #8242
Attention encoder-decoder models for multiple speech-to-text tasks #8242
Changes from 1 commit
c914fcd
786adbe
702d22f
41bcf87
d53b3c8
4c532d7
d5525bf
e0a214d
02551f3
27999c9
6b3e18d
b0d6f19
955eb14
dd2c97f
e63db16
5ccd1a1
ddfc788
1fbbfc9
5e7cd02
2fd5b9d
993550d
f732b0b
86a3f18
a595213
9b7aa0f
ee16e5c
05157f7
780d107
1047695
5fe0daa
da39af6
2579687
aacdd1e
6a2d6e2
9bcaa08
e1cbea3
e429954
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is this necessary ? There are so many more modules for Multi Task models - please add remainder or remove this section
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we probably shouldn't mandate that. @krishnacpuvvada WDYT?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we shouldn't mandate. but, we also want to highlight that large models greatly benefit from (or often require) initializing encoder at the minimum. Lets keep the argument but change
???
to None and leave a comment.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Lets update this docstring to support Multi task models
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
could you be more specific? I can't see what needs changing
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The docstring has args that don't actually get used to train the model - we need a docstring with lhotse args for data and a override of using model_defaults.encoder_hidden=xyz to shoe how to override main args on this model
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done