Complete the translate function below by replacing all None placeholders with proper parameters.

This function will take care of the following steps:

Process the sentence to translate and encode it

Set the initial state of the decoder

Get predictions of the next token $($starting with the token$)$ for a maximum of iterations $($in case the token is never returned$)$

Return the translated text $($as a string$),$ the logit of the last iteration $($this helps measure how certain was that the sequence was translated in its totality$)$ and the translation in token format.

def translate$($model$,$ text, max$\_$length$=50,$ temperature$=0\mathrm{.}0)$:

$"""$Translate a given sentence from English to Portuguese

Args:

model $($tf$.$keras.Model$)$: The trained translator

text $($string$)$: The sentence to translate

max$\_$length $($int$,$ optional$)$: The maximum length of the translation. Defaults to $50.$

temperature $($float$,$ optional$)$: The temperature that controls the randomness of the predicted tokens. Defaults to $0\mathrm{.}0.$

Returns:

tuple$($str$,$ np$.$float, tf$.$Tensor$)$: The translation, logit that predicted token and the tokenized translation

$"""$

# Lists to save tokens and logits

tokens, logits $=[],[]$

### START CODE HERE ###

# PROCESS THE SENTENCE TO TRANSLATE

# Convert the original string into a tensor

text $=$ tf$.$None$($None$)[$tf$.$None$]$

# Vectorize the text using the correct vectorizer

context $=$ None$($None$).$to$\_$tensor$()$

# Get the encoded context $($pass the context through the encoder$)$

# Hint: Remember you can get the encoder by using model.encoder

context $=$ None.None$($None$)$

# INITIAL STATE OF THE DECODER

# First token should be SOS token with shape $(1,1)$

next$\_$token $=$ tf$.$None$(($None$,$ None$),$ None$)$

# Initial hidden and cell states should be tensors of zeros with shape $(1,$ UNITS$)$

state $=[$tf$.$None$(($None$,$ None$)),$ tf$.$None$(($None$,$ None$))]$

# You are done when you draw a EOS token as next token $($initial state is False$)$

done $=$ None

# Iterate for max$\_$length iterations

for None in None$($None$)$:

# Generate the next token

try:

next$\_$token, logit$,$ state, done $=$ None$($

decoder$=$None,

context$=$None,

next$\_$token$=$None,

done$=$None,

state$=$None,

temperature$=$None

$)$

except:

raise Exception$("$Problem generating the next token"$)$

# If done then break out of the loop

if None:

None

# Add next$\_$token to the list of tokens

None.None$($None$)$

# Add logit to the list of logits

None.None$($None$)$

### END CODE HERE ###

# Concatenate all tokens into a tensor

tokens $=$ tf$.$concat$($tokens$,$ axis$=-1)$

# Convert the translated tokens into text

translation $=$ tf$.$squeeze$($tokens$\_$to$\_$text$($tokens$,$ id$\_$to$\_$word$))$

translation $=$ translation.numpy$().$decode$()$

return translation, logits$[-1],$ tokens