Model layer is not compatible

Question

ValueError: Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 238), found shape=(None, 30, 1662)

I have this error. So I read that I need to fix my model definition. I tried to change my parameter, however, I keep stuck with the same problem

This is my model

tf.keras.backend.clear_session()
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional
from tensorflow.keras import Input, Model

input1 = Input(shape=(maxlen,))
X = Embedding(vocab_size, 64)(input1)
X = LSTM(64)(X)
out = Dense(1, activation='relu')(X)

model = Model(inputs=[input1], outputs=[out])
model.summary()

I use maxlen as my dataset has different sizes per class with max length of 521