tensorflow: tf.lite.TFLiteConverter crashes when converting Keras model

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): OSX 10.15.5- TensorFlow installed from (source or binary): binary
• TensorFlow version (use command below): v1.12.1-37224-ga6cd18a133 2.4.0-dev20200722
• Python version: 3.7

Describe the current behavior It throws exception

Describe the expected behavior It should finish the conversion successfully

Standalone code to reproduce the issue

import numpy as np
import tensorflow as tf

model = tf.keras.models.Sequential([
    tf.keras.layers.Input(shape=(28, 28), name='input'),
    tf.keras.layers.Bidirectional(
        tf.keras.layers.LSTM(20, return_sequences=True)),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(10, activation=tf.nn.softmax, name='output')
])
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model.summary()

run_model = tf.function(lambda x: model(x))
# This is important, let's fix the input size.
BATCH_SIZE = 1
STEPS = 28
INPUT_SIZE = 28
concrete_func = run_model.get_concrete_function(
    tf.TensorSpec([BATCH_SIZE, STEPS, INPUT_SIZE], model.inputs[0].dtype))

# model directory.
MODEL_DIR = "keras_lstm"

# converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func])
# converter = tf.lite.TFLiteConverter.from_saved_model(MODEL_DIR)
converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.experimental_new_converter = True
tflite_model = converter.convert()

with tf.io.gfile.GFile('tflite_test.tflite', 'wb') as f:
    f.write(tflite_model)