[Wav2Vec2] Fix dtype 64 bug (#13517)

* fix

* 2nd fix

docs/source/conf.py

@@ -27,7 +27,8 @@ author = "huggingface"
 # The short X.Y version
 version = ""
 # The full version, including alpha/beta/rc tags
-release = "4.10.1"
+release = "4.10.2"
+
 
 
 

setup.py

@@ -342,7 +342,7 @@ install_requires = [
 
 setup(
     name="transformers",
-    version="4.10.1",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="4.10.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Sam Shleifer, Patrick von Platen, Sylvain Gugger, Suraj Patil, Stas Bekman, Google AI Language Team Authors, Open AI team Authors, Facebook AI Authors, Carnegie Mellon University Authors",
     author_email="thomas@huggingface.co",
     description="State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch",

src/transformers/__init__.py

@@ -22,7 +22,7 @@
 # to defer the actual importing for when the objects are requested. This way `import transformers` provides the names
 # in the namespace without actually importing anything (and especially none of the backends).
 
-__version__ = "4.10.1"
+__version__ = "4.10.2"
 
 # Work around to update TensorFlow's absl.logging threshold which alters the
 # default Python logging output behavior when present.

src/transformers/models/speech_to_text/feature_extraction_speech_to_text.py

@@ -210,7 +210,7 @@ class Speech2TextFeatureExtractor(SequenceFeatureExtractor):
             raw_speech = [np.asarray(speech) for speech in raw_speech]
         elif not is_batched and not isinstance(raw_speech, np.ndarray):
             raw_speech = np.asarray(raw_speech)
-        elif isinstance(raw_speech, np.ndarray) and raw_speech.dtype is np.float64:
+        elif isinstance(raw_speech, np.ndarray) and raw_speech.dtype is np.dtype(np.float64):
             raw_speech = raw_speech.astype(np.float32)
 
         # always return batch

src/transformers/models/wav2vec2/feature_extraction_wav2vec2.py

@@ -207,10 +207,10 @@ class Wav2Vec2FeatureExtractor(SequenceFeatureExtractor):
         elif (
             not isinstance(input_values, np.ndarray)
             and isinstance(input_values[0], np.ndarray)
-            and input_values[0].dtype is np.float64
+            and input_values[0].dtype is np.dtype(np.float64)
         ):
             padded_inputs["input_values"] = [array.astype(np.float32) for array in input_values]
-        elif isinstance(input_values, np.ndarray) and input_values.dtype is np.float64:
+        elif isinstance(input_values, np.ndarray) and input_values.dtype is np.dtype(np.float64):
             padded_inputs["input_values"] = input_values.astype(np.float32)
 
         # convert attention_mask to correct format