replace `Speech2TextTokenizer` by `Speech2TextFeatureExtractor` in some docstrings (#16835)

* replace `Speech2TextTokenizer` by `Speech2TextFeatureExtractor` in docstring

* quality

src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py

@@ -139,8 +139,8 @@ SPEECH_ENCODER_DECODER_INPUTS_DOCSTRING = r"""
             Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be obtained
             by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a `numpy.ndarray`, *e.g.*
             via the soundfile library (`pip install soundfile`). To prepare the array into `input_features`, the
-            [`Speech2TextTokenizer`] should be used for extracting the fbank features, padding and conversion into a
-            tensor of type `torch.FloatTensor`. See [`~Speech2TextTokenizer.__call__`]
+            [`Speech2TextFeatureExtractor`] should be used for extracting the fbank features, padding and conversion
+            into a tensor of type `torch.FloatTensor`. See [`~Speech2TextFeatureExtractor.__call__`]
         return_dict (`bool`, *optional*):
             If set to `True`, the model will return a [`~utils.Seq2SeqLMOutput`] instead of a plain tuple.
         kwargs: (*optional*) Remaining dictionary of keyword arguments. Keyword arguments come in two flavors:

src/transformers/models/speech_to_text/modeling_speech_to_text.py

@@ -600,8 +600,8 @@ SPEECH_TO_TEXT_INPUTS_DOCSTRING = r"""
             Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be obtained
             by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a `numpy.ndarray`, *e.g.*
             via the soundfile library (`pip install soundfile`). To prepare the array into `input_features`, the
-            [`Speech2TextTokenizer`] should be used for extracting the fbank features, padding and conversion into a
-            tensor of type `torch.FloatTensor`. See [`~Speech2TextTokenizer.__call__`]
+            [`Speech2TextFeatureExtractor`] should be used for extracting the fbank features, padding and conversion
+            into a tensor of type `torch.FloatTensor`. See [`~Speech2TextFeatureExtractor.__call__`]
         attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
             Mask to avoid performing convolution and attention on padding token indices. Mask values selected in `[0,
             1]`:
@@ -733,9 +733,9 @@ class Speech2TextEncoder(Speech2TextPreTrainedModel):
                 Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be
                 obtained by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a
                 `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into
-                `input_features`, the [`Speech2TextTokenizer`] should be used for extracting the fbank features,
+                `input_features`, the [`Speech2TextFeatureExtractor`] should be used for extracting the fbank features,
                 padding and conversion into a tensor of type `torch.FloatTensor`. See
-                [`~Speech2TextTokenizer.__call__`]
+                [`~Speech2TextFeatureExtractor.__call__`]
             attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                 Mask to avoid performing convolution and attention on padding token indices. Mask values selected in
                 `[0, 1]`:

src/transformers/models/speech_to_text/modeling_tf_speech_to_text.py

@@ -650,8 +650,8 @@ SPEECH_TO_TEXT_INPUTS_DOCSTRING = r"""
             Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be obtained
             by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a `numpy.ndarray`, *e.g.*
             via the soundfile library (`pip install soundfile`). To prepare the array into `input_features`, the
-            [`Speech2TextTokenizer`] should be used for extracting the fbank features, padding and conversion into a
-            tensor of floats. See [`~Speech2TextTokenizer.__call__`]
+            [`Speech2TextFeatureExtractor`] should be used for extracting the fbank features, padding and conversion
+            into a tensor of floats. See [`~Speech2TextFeatureExtractor.__call__`]
         attention_mask (`tf.Tensor` of shape `({0})`, *optional*):
             Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:
 
@@ -798,8 +798,8 @@ class TFSpeech2TextEncoder(tf.keras.layers.Layer):
                 Float values of fbank features extracted from the raw speech waveform. Raw speech waveform can be
                 obtained by loading a `.flac` or `.wav` audio file into an array of type `List[float]` or a
                 `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into
-                `input_features`, the [`Speech2TextTokenizer`] should be used for extracting the fbank features,
-                padding and conversion into a tensor of floats. See [`~Speech2TextTokenizer.__call__`]
+                `input_features`, the [`Speech2TextFeatureExtractor`] should be used for extracting the fbank features,
+                padding and conversion into a tensor of floats. See [`~Speech2TextFeatureExtractor.__call__`]
             attention_mask (`tf.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                 Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: