Add Initial support for ContextNet Encoder and CTC Decoder #630
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
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
okuchaiev
requested changes
May 13, 2020
nemo/collections/asr/contextnet.py
Outdated
| logging = nemo.logging | ||
|
|
||
|
|
||
| class ContextNetEncoder(TrainableNM): |
There was a problem hiding this comment.
Should this inherit from JasperEncoder ?
There was a problem hiding this comment.
On second thought, it probably should not inherit JasperEncoder. While yes currently they share exactly same functionality, in the future they will not. In that case, the __init__ call will instantiate multiple JasperBlocks before ContextNetEncoder starts to instantiate its own values.
While there is duplication for now, it is cleaner to separate the two modules
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
Signed-off-by: smajumdar <[email protected]>
|
This pull request introduces 1 alert when merging 8c81303 into a22d325 - view on LGTM.com new alerts:
|
Signed-off-by: smajumdar <[email protected]>
blisc
previously approved these changes
May 14, 2020
|
|
||
| # (ContextNet uses the Jasper baseline encoder and decoder) | ||
| encoder = nemo_asr.ContextNetEncoder( | ||
| feat_in=contextnet_params["AudioToMelSpectrogramPreprocessor"]["features"], |
There was a problem hiding this comment.
Just a note that you can add this inside the yaml itself.
See https://confluence.atlassian.com/bitbucket/yaml-anchors-960154027.html
There was a problem hiding this comment.
Thanks for the hint !
Signed-off-by: smajumdar <[email protected]>
|
This pull request introduces 1 alert when merging 81330ba into a22d325 - view on LGTM.com new alerts:
|
Signed-off-by: smajumdar <[email protected]>
okuchaiev
approved these changes
May 16, 2020
ZeroCool940711
pushed a commit
to ZeroCool940711/NeMo
that referenced
this pull request
May 16, 2020
* Add SE + context SE support Signed-off-by: smajumdar <[email protected]> * Add contextnet components Signed-off-by: smajumdar <[email protected]> * Add ContextNet support Signed-off-by: smajumdar <[email protected]> * Add config files Signed-off-by: smajumdar <[email protected]> * Correct configs Signed-off-by: smajumdar <[email protected]> * Add streaming speech command Signed-off-by: smajumdar <[email protected]> * Add kernel size factor argument Signed-off-by: smajumdar <[email protected]> * Add docstrings Signed-off-by: smajumdar <[email protected]> * Update CHANGELOG.md Signed-off-by: smajumdar <[email protected]> * Add integration tests Signed-off-by: smajumdar <[email protected]> * Style fixes and add docstrings for se_reduction_ratio Signed-off-by: smajumdar <[email protected]> * Style fixes in tests Signed-off-by: smajumdar <[email protected]> * Correct CHANGELOG.md Signed-off-by: smajumdar <[email protected]> * Correctios to docstrings Signed-off-by: smajumdar <[email protected]> * Add WandB support to contextnet.py Signed-off-by: smajumdar <[email protected]> * Style fixes Signed-off-by: smajumdar <[email protected]> * Remove unused import Signed-off-by: smajumdar <[email protected]> * Refactor ContextNetEncoder to subclass JasperEncoder Signed-off-by: smajumdar <[email protected]> * Remove unused imports Signed-off-by: smajumdar <[email protected]> Signed-off-by: ZeroCool <[email protected]>
dcurran90
pushed a commit
to dcurran90/NeMo
that referenced
this pull request
Oct 15, 2024
Use a single jinja template for the prompts with and without a document. Also remove the conditionals checking for te presence of a document. Fixes NVIDIA#629 Signed-off-by: Derek Higgins <[email protected]>
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.
Changelog
Added
stride_lastflag which allowsstrideandrepeatflags to be used simultaneously. It will perform the strided convolution at the final Conv-BN-ReLU sub-block.swishas optional activation functionzero_infinityflag toCTCLoss, default to False.Modified
se_reduction_ratioto 8 instead of 16.SpecAugmentnow supports either an integer or floating point value fortime_width.Note: Currently,
examples/asr/contextnet.pyuses JasperDecoderForCTC instead of ContextNetDecoderForCTC. This will be updated in a future PR once full support is present.