fairseq/tests/speech_recognition
Marco Gaido 5453e4355b Avoid NaN in speech_recognition with input having only 1 spec… (#1864)
Summary:
…trogram

# Before submitting

- [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements)
- [x] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/master/CONTRIBUTING.md)?
- [ ] Did you make sure to update the docs?
- [x] Did you write any new necessary tests?

## What does this PR do?
Fixes https://github.com/pytorch/fairseq/issues/1863.

## PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

## Did you have fun?
Make sure you had fun coding �
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1864

Reviewed By: yqwangustc

Differential Revision: D21663642

Pulled By: myleott

fbshipit-source-id: f411c5c01c7505375bec6d47554e85fb70877e9c
2020-05-27 07:50:34 -07:00
..
__init__.py Asr initial push (#810) 2019-08-08 02:46:12 -07:00
asr_test_base.py refactor namespaces in criterion interface (#1729) 2020-03-04 16:43:59 -08:00
test_collaters.py Small fixes 2019-08-19 15:08:25 -07:00
test_cross_entropy.py Small fixes 2019-08-19 15:08:25 -07:00
test_data_utils.py Avoid NaN in speech_recognition with input having only 1 spec… (#1864) 2020-05-27 07:50:34 -07:00
test_vggtransformer.py Asr initial push (#810) 2019-08-08 02:46:12 -07:00