How to use a tensorflow .h5 model in tensorflow js within the browser?

Question

I am currently studying with the book practical introduction with keras and tensorflow 2.0. I just ran the example of a recurrent neural network text generator and with python everything works fine for me. Now I want to use the generated model with h5 extension from tensorflow js to generate text and I don't understand how I could do it

source code link https://github.com/jorditorresBCN/python-deep-learning/blob/master/13_Redes_neuronales_recurrentes.ipynb

This is the function used in the book to generate text in python, but I don't know if I should do the same thing in javascript with tensorflow js

def generate_text(model, start_string):
  num_generate = 500
  input_eval = [char2idx[s] for s in start_string]
  input_eval = tf.expand_dims(input_eval, 0)
  text_generated = []
  temperature = 0.5
  model.reset_states()
  for i in range(num_generate):
      predictions = model(input_eval)
      predictions = tf.squeeze(predictions, 0)
      predictions = predictions / temperature
      predicted_id = tf.random.categorical(predictions, num_samples=1)[-1,0].numpy()
      input_eval = tf.expand_dims([predicted_id], 0)
      text_generated.append(idx2char[predicted_id])
  return (start_string + ''.join(text_generated))

I have already converted the h5 model into the json model that supports tensorflow js and I can also load it from the web browser, but I do not understand how I can use the model to generate text from with tensorflow js

Could someone help me with the steps to build the functionality in javascript that allows me to generate text with the model?