fix SpeechRecognitionOutputTransform if local (#1362)

Co-authored-by: Ethan Harris <[email protected]>
Lightning-Universe · Jun 29, 2022 · ee512a2 · ee512a2
1 parent 345c95c
commit ee512a2
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -40,6 +40,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 - Fixed naming of optimizer and scheduler registries which did not allow manual optimization. ([#1342](https://github.com/PyTorchLightning/lightning-flash/pull/1342))
 
+- Fixed a bug where the `processor_backbone` argument to `SpeechRecognition` was not used for decoding outputs ([#1362](https://github.com/PyTorchLightning/lightning-flash/pull/1362))
+
 ## [0.7.4] - 2022-04-27
 
 ### Fixed

diff --git a/flash/audio/speech_recognition/model.py b/flash/audio/speech_recognition/model.py
@@ -71,7 +71,9 @@ def __init__(
             optimizer=optimizer,
             lr_scheduler=lr_scheduler,
             learning_rate=learning_rate,
-            output_transform=SpeechRecognitionOutputTransform(backbone),
+            output_transform=SpeechRecognitionOutputTransform(backbone)
+            if processor_backbone is None
+            else SpeechRecognitionOutputTransform(processor_backbone),
         )
 
         self.save_hyperparameters()