fix: apply channel averaging correctly in audio feature extractors

src/transformers/models/cohere_asr/feature_extraction_cohere_asr.py

@@ -284,17 +284,17 @@ def __call__(
                 f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                 "We will take the mean of the channels to convert to mono."
             )
-            raw_speech = raw_speech.mean(-1)
+            raw_speech = raw_speech.mean(1)
 
         is_batched_sequence = isinstance(raw_speech, (list, tuple))
         if is_batched_sequence:
-            for speech in raw_speech:
+            for index, speech in enumerate(raw_speech):
                 if len(speech.shape) > 1:
                     logger.warning(
                         f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                         "We will take the mean of the channels to convert to mono."
                     )
-                    speech = speech.mean(-1)
+                    raw_speech[index] = speech.mean(0)
 
         if is_batched_torch or is_batched_sequence:
             raw_speech = [speech.to(torch.float32) for speech in raw_speech]

src/transformers/models/lasr/feature_extraction_lasr.py

@@ -232,17 +232,17 @@ def __call__(
                 f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                 "We will take the mean of the channels to convert to mono."
             )
-            raw_speech = raw_speech.mean(-1)
+            raw_speech = raw_speech.mean(1)
 
         is_batched_sequence = isinstance(raw_speech, (list, tuple))
         if is_batched_sequence:
-            for speech in raw_speech:
+            for index, speech in enumerate(raw_speech):
                 if len(speech.shape) > 1:
                     logger.warning(
                         f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                         "We will take the mean of the channels to convert to mono."
                     )
-                    speech = speech.mean(-1)
+                    raw_speech[index] = speech.mean(0)
 
         if is_batched_torch or is_batched_sequence:
             raw_speech = [speech[:, None].to(torch.float32) for speech in raw_speech]

src/transformers/models/parakeet/feature_extraction_parakeet.py

@@ -217,17 +217,17 @@ def __call__(
                 f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                 "We will take the mean of the channels to convert to mono."
             )
-            raw_speech = raw_speech.mean(-1)
+            raw_speech = raw_speech.mean(1)
 
         is_batched_sequence = isinstance(raw_speech, (list, tuple))
         if is_batched_sequence:
-            for speech in raw_speech:
+            for index, speech in enumerate(raw_speech):
                 if len(speech.shape) > 1:
                     logger.warning(
                         f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                         "We will take the mean of the channels to convert to mono."
                     )
-                    speech = speech.mean(-1)
+                    raw_speech[index] = speech.mean(0)
 
         if is_batched_torch or is_batched_sequence:
             raw_speech = [speech[:, None].to(torch.float32) for speech in raw_speech]

src/transformers/models/phi4_multimodal/feature_extraction_phi4_multimodal.py

@@ -145,17 +145,17 @@ def __call__(
                 f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                 "We will take the mean of the channels to convert to mono."
             )
-            raw_speech = raw_speech.mean(-1)
+            raw_speech = raw_speech.mean(1)
 
         is_batched_sequence = isinstance(raw_speech, (list, tuple))
         if is_batched_sequence:
-            for speech in raw_speech:
+            for index, speech in enumerate(raw_speech):
                 if len(speech.shape) > 1:
                     logger.warning(
                         f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                         "We will take the mean of the channels to convert to mono."
                     )
-                    speech = speech.mean(-1)
+                    raw_speech[index] = speech.mean(0)
 
         if is_batched_torch or is_batched_sequence:
             raw_speech = [speech[:, None].to(torch.float32) for speech in raw_speech]

src/transformers/models/voxtral_realtime/feature_extraction_voxtral_realtime.py

@@ -203,17 +203,17 @@ def __call__(
                 f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                 "We will take the mean of the channels to convert to mono."
             )
-            raw_speech = raw_speech.mean(-1)
+            raw_speech = raw_speech.mean(1)
 
         is_batched_sequence = isinstance(raw_speech, (list, tuple))
         if is_batched_sequence:
-            for speech in raw_speech:
+            for index, speech in enumerate(raw_speech):
                 if len(speech.shape) > 1:
                     logger.warning(
                         f"Only mono-channel audio is supported for input to {self.__class__.__name__}. "
                         "We will take the mean of the channels to convert to mono."
                     )
-                    speech = speech.mean(-1)
+                    raw_speech[index] = speech.mean(0)
 
         if is_batched_torch or is_batched_sequence:
             raw_speech = [speech[:, None].to(torch.float32) for speech in raw_speech]