Change Keras preprocessing APIs to stable in the Simple audio recognition tutorial

PiperOrigin-RevId: 405733610

Author: tensorflower-gardener

site/en/tutorials/audio/simple_audio.ipynb

@@ -104,7 +104,6 @@
         "import seaborn as sns\n",
         "import tensorflow as tf\n",
         "\n",
-        "from tensorflow.keras.layers.experimental import preprocessing\n",
         "from tensorflow.keras import layers\n",
         "from tensorflow.keras import models\n",
         "from IPython import display\n",
@@ -620,9 +619,9 @@
       },
       "source": [
         "For the model, you'll use a simple convolutional neural network (CNN), since you have transformed the audio files into spectrogram images.\n",
-        "The model also has the following additional preprocessing layers:\n",
-        "- A [`Resizing`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/experimental/preprocessing/Resizing) layer to downsample the input to enable the model to train faster.\n",
-        "- A [`Normalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/experimental/preprocessing/Normalization) layer to normalize each pixel in the image based on its mean and standard deviation.\n",
+        "The model also has the following additional Keras preprocessing layers:\n",
+        "- `tf.keras.layers.Resizing`: to downsample the input to enable the model to train faster.\n",
+        "- `tf.keras.layers.Normalization`: to normalize each pixel in the image based on its mean and standard deviation.\n",
         "\n",
         "For the `Normalization` layer, its `adapt` method would first need to be called on the training data in order to compute aggregate statistics (i.e. mean and standard deviation)."
       ]
@@ -640,12 +639,12 @@
         "print('Input shape:', input_shape)\n",
         "num_labels = len(commands)\n",
         "\n",
-        "norm_layer = preprocessing.Normalization()\n",
+        "norm_layer = layers.Normalization()\n",
         "norm_layer.adapt(spectrogram_ds.map(lambda x, _: x))\n",
         "\n",
         "model = models.Sequential([\n",
         "    layers.Input(shape=input_shape),\n",
-        "    preprocessing.Resizing(32, 32), \n",
+        "    layers.Resizing(32, 32), \n",
         "    norm_layer,\n",
         "    layers.Conv2D(32, 3, activation='relu'),\n",
         "    layers.Conv2D(64, 3, activation='relu'),\n",