Allow FP16 or other precision inference for Pipelines (#31342)

* cast image features to model.dtype where needed to support FP16 or other precision in pipelines

* Update src/transformers/pipelines/image_feature_extraction.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Use .to instead

* Add FP16 pipeline support for zeroshot audio classification

* Remove unused torch imports

* Add docs on FP16 pipeline

* Remove unused import

* Add FP16 tests to pipeline mixin

* Add fp16 placeholder for mask_generation pipeline test

* Add FP16 tests for all pipelines

* Fix formatting

* Remove torch_dtype arg from is_pipeline_test_to_skip*

* Fix format

* trigger ci

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

tests/pipelines/test_pipelines_automatic_speech_recognition.py

@@ -66,14 +66,14 @@ class AutomaticSpeechRecognitionPipelineTests(unittest.TestCase):
         + (MODEL_FOR_CTC_MAPPING.items() if MODEL_FOR_CTC_MAPPING else [])
     )
 
-    def get_test_pipeline(self, model, tokenizer, processor):
+    def get_test_pipeline(self, model, tokenizer, processor, torch_dtype="float32"):
         if tokenizer is None:
             # Side effect of no Fast Tokenizer class for these model, so skipping
             # But the slow tokenizer test should still run as they're quite small
             self.skipTest(reason="No tokenizer available")
 
         speech_recognizer = AutomaticSpeechRecognitionPipeline(
-            model=model, tokenizer=tokenizer, feature_extractor=processor
+            model=model, tokenizer=tokenizer, feature_extractor=processor, torch_dtype=torch_dtype
         )
 
         # test with a raw waveform