ValueError: Input 0 of layer sequential_2 is incompatible with the layer Tensorflow

tfidf_text.shape
(3113, 3834)

labels = df.label.values

x_train, x_valid, y_train, y_valid = train_test_split(tfidf_text, labels, test_size=0.1, stratify=labels)

n_classes = df.label.nunique()

batch_size = 4
epochs = 50
num_neurons = 100

n_model = Sequential()
n_model.add(LSTM(num_neurons, return_sequences=True, input_shape=(3113, 3834)))
n_model.add(Dropout(.2))
n_model.add(Flatten())
n_model.add(Dense(n_classes, activation="softmax"))
n_model.compile(optimizer='rmsprop',  loss = CategoricalCrossentropy(), metrics=[Precision(), Recall()])

n_model.summary()

n_model.fit(x_train, y_train,
         batch_size=batch_size,
         epochs=epochs,
         validation_data=(x_valid, y_valid))

Как исправить ошибку:

ValueError                                Traceback (most recent call last)
<ipython-input-75-3d68aa27dfae> in <module>()
      2          batch_size=batch_size,
      3          epochs=epochs,
----> 4          validation_data=(x_valid, y_valid))

9 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    /usr/local/lib/python3.7/dist-packages/keras/engine/training.py:853 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.7/dist-packages/keras/engine/training.py:842 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/keras/engine/training.py:835 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.7/dist-packages/keras/engine/training.py:787 train_step
        y_pred = self(x, training=True)
    /usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py:1020 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
    /usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py:218 assert_input_compatibility
        str(tuple(shape)))

    ValueError: Input 0 of layer sequential_6 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 3834)