[ASR pipline] fix with datasets 4.0 (huggingface#39504)

* fix

* handle edge case

* make

Author: eustlb

src/transformers/pipelines/automatic_speech_recognition.py

@@ -380,7 +380,11 @@ def preprocess(self, inputs, chunk_length_s=0, stride_length_s=None):
 
             if isinstance(inputs, torchcodec.decoders.AudioDecoder):
                 _audio_samples = inputs.get_all_samples()
+
+                # torchcodec always returns (num_channels, num_samples)
+                # while before (datasets < 4.0) we had (2, num_samples) if stereo, (num_samples,) if mono
                 _array = _audio_samples.data
+                _array = _array[0] if _array.ndim == 2 and _array.shape[0] == 1 else _array
                 inputs = {"array": _array, "sampling_rate": _audio_samples.sample_rate}
 
         if isinstance(inputs, dict):
@@ -429,10 +433,13 @@ def preprocess(self, inputs, chunk_length_s=0, stride_length_s=None):
                 # can add extra data in the inputs, so we need to keep track
                 # of the original length in the stride so we can cut properly.
                 stride = (inputs.shape[0], int(round(stride[0] * ratio)), int(round(stride[1] * ratio)))
-        if not isinstance(inputs, np.ndarray):
+        if not isinstance(inputs, (np.ndarray, torch.Tensor)):
             raise TypeError(f"We expect a numpy ndarray or torch tensor as input, got `{type(inputs)}`")
-        if len(inputs.shape) != 1:
-            raise ValueError("We expect a single channel audio input for AutomaticSpeechRecognitionPipeline")
+        if inputs.ndim != 1:
+            logger.warning(
+                f"We expect a single channel audio input for AutomaticSpeechRecognitionPipeline, got {inputs.ndim}. Taking the mean of the channels for mono conversion."
+            )
+            inputs = inputs.mean(axis=0)
 
         if chunk_length_s:
             if stride_length_s is None: