Commit b986e9ef authored by Zhaoheng Ni's avatar Zhaoheng Ni Committed by Facebook GitHub Bot
Browse files

Fix TimeMasking argument in TED-LIUM Emformer recipe (#2199)

Summary: Pull Request resolved: https://github.com/pytorch/audio/pull/2199

Reviewed By: hwangjeff

Differential Revision: D33979923

Pulled By: nateanl

fbshipit-source-id: 566ba1944dd3511fee740ac17fea2dcb0e5810fa
parent 8f68b3f0
...@@ -147,8 +147,8 @@ class RNNTModule(LightningModule): ...@@ -147,8 +147,8 @@ class RNNTModule(LightningModule):
FunctionalModule(lambda x: x.transpose(1, 2)), FunctionalModule(lambda x: x.transpose(1, 2)),
torchaudio.transforms.FrequencyMasking(27), torchaudio.transforms.FrequencyMasking(27),
torchaudio.transforms.FrequencyMasking(27), torchaudio.transforms.FrequencyMasking(27),
TimeMasking(100, 0.2), TimeMasking(100, p=0.2),
TimeMasking(100, 0.2), TimeMasking(100, p=0.2),
FunctionalModule(lambda x: torch.nn.functional.pad(x, (0, 4))), FunctionalModule(lambda x: torch.nn.functional.pad(x, (0, 4))),
FunctionalModule(lambda x: x.transpose(1, 2)), FunctionalModule(lambda x: x.transpose(1, 2)),
) )
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment