Commits · fdea0a7c65ee80cafce82bb27a40fbc4a4c02bb0 · OpenDAS / Torchaudio

16 Feb, 2022 4 commits

Refactor pipeline_demo script in emformer_rnnt recipes (#2239) · fdea0a7c

Zhaoheng Ni authored Feb 16, 2022

Summary:
- Use dictionary to select the `RNNTBundle` and the corresponding dataset.
- Use the dictionary's keys as choices in ArgumentParser

Pull Request resolved: https://github.com/pytorch/audio/pull/2239

Reviewed By: mthrok

Differential Revision: D34267070

Pulled By: nateanl

fbshipit-source-id: 99c7942d5c7c1518694e1ae02a55a7decd87c220

fdea0a7c

Refactor eval and pipeline_demo scripts in emformer_rnnt (#2238) · e3b40d1c

Zhaoheng Ni authored Feb 16, 2022

Summary:
- Add docstring to `eval.py` and `pipeline_demo.py` under `emformer_rnnt` directory.
- Refactor logger and ArgumentParser

Pull Request resolved: https://github.com/pytorch/audio/pull/2238

Reviewed By: mthrok

Differential Revision: D34267059

Pulled By: nateanl

fbshipit-source-id: 4b8d3d183ee7bc0ad71ce305cab87bfa90208b2e

e3b40d1c

Add shebang lines to scripts in emformer_rnnt recipes (#2237) · aac83fe5

Zhaoheng Ni authored Feb 16, 2022

Summary: Pull Request resolved: https://github.com/pytorch/audio/pull/2237

Reviewed By: mthrok

Differential Revision: D34267000

Pulled By: nateanl

fbshipit-source-id: 4c264aea6cf3fba5d8728d5fe60f9f471815852d

aac83fe5

Refactor ArgumentParser arguments in emformer_rnnt recipes (#2236) · 81f56f64

Zhaoheng Ni authored Feb 16, 2022

Summary:
Replace underscore with dash in ArgumentParser's arguments.

Pull Request resolved: https://github.com/pytorch/audio/pull/2236

Reviewed By: mthrok

Differential Revision: D34266977

Pulled By: nateanl

fbshipit-source-id: ceacac12c04016a8dbf2a1a7d6bbcf65d4d53d21

81f56f64

11 Feb, 2022 1 commit

Refactor pipeline_demo.py to support variant EMFORMER_RNNT bundles (#2203) · 16d02a9e

nateanl authored Feb 11, 2022

Summary:
We refactored the demo script that can apply RNNT decoding using both `torchaudio.pipelines.EMFORMER_RNNT_BASE_LIBRISPEECH` and `torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_TEDLIUM3` in both streaming and non-streaming mode. (The first hypothesis prediction is streaming and the second one is non-streaming).

We convert each token id sequence to word pieces and then manually join the word pieces. This allows us to preserve leading whitespaces on output strings and therefore account for word breaks and continuations across token processor invocations, which is particularly useful when performing streaming ASR.

https://user-images.githubusercontent.com/8653221/153627956-f0806f18-3c1c-44df-ac07-ec2def58a0cf.mov

Pull Request resolved: https://github.com/pytorch/audio/pull/2203

Reviewed By: carolineechen

Differential Revision: D34006388

Pulled By: nateanl

fbshipit-source-id: 3d31173ee10cdab8a2f5802570e22b50fcce5632

16d02a9e