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

Streaming merge #369

Merged
merged 263 commits into from
May 15, 2022
Merged

Streaming merge #369

merged 263 commits into from
May 15, 2022

Conversation

yaozengwei
Copy link
Collaborator

Merge change of master branch into streaming branch.

csukuangfj and others added 29 commits May 3, 2022 07:02
* Save batch to disk on OOM.

* minor fixes

* Fixes after review.

* Fix style issues.
* First upload of model average codes.

* minor fix

* update decode file

* update .flake8

* rename pruned_transducer_stateless3 to pruned_transducer_stateless4

* change epoch number counter starting from 1 instead of 0

* minor fix of pruned_transducer_stateless4/train.py

* refactor the checkpoint.py

* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py

* update author info

* add docs of the scaling in function average_checkpoints_with_averaged_model
* keep model_avg on cpu

* explicitly convert model_avg to cpu

* minor fix

* remove device convertion for model_avg

* modify usage of the model device in train.py

* change model.device to next(model.parameters()).device for decoding

* assert params.start_epoch>0

* assert params.start_epoch>0, params.start_epoch
…a#347)

* do some changes for aishell/ASR/transducer_stateless/export.py
* support decoding with averaged model when using --iter

* minor fix

* monir fix of copyright date
* Ignore padding frames during RNN-T decoding.

* Fix outdated decoding code.

* Minor fixes.
* Copy RNN-T recipe from librispeech

* flake8

* flake8

* Update params

* gigaspeech decode

* black

* Update results

* syntax highlight

* Update RESULTS.md

* typo
)

* Validate that there are no OOV tokens in BPE-based lexicons.

* Typo fixes.
* Update results for libri+giga multi dataset setup.
* Update decode.py

* Update export.py

* Update results

* Update README.md
@yaozengwei yaozengwei merged commit a9dccdc into k2-fsa:streaming May 15, 2022
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

Successfully merging this pull request may close these issues.

9 participants