Seq2Seq-LSTM-MultiHeadAttention

import numpy as np
from tensorflow.keras.preprocessing.sequence import pad_sequences

def preprocess_input(sentence, word2idx_en, max_seq_len, oov_token="<OOV>"):
    oov_idx = word2idx_en[oov_token]
    seq = [word2idx_en.get(w.lower(), oov_idx) for w in sentence.split()]
    return pad_sequences([seq], maxlen=max_seq_len, padding='post')

def decode_sequence(input_seq, encoder_model, decoder_model, word2idx_hi, idx2word_hi, max_seq_len):
    start_token = word2idx_hi['<start>']
    end_token = word2idx_hi['<end>']

    enc_outs, h, c = encoder_model.predict(input_seq, verbose=0)
    target_seq = np.array([[start_token]])
    decoded_sentence = []

    for _ in range(max_seq_len):
        output_tokens, h, c = decoder_model.predict([target_seq, h, c, enc_outs], verbose=0)
        sampled_idx = np.argmax(output_tokens[0,0,:])
        if sampled_idx == end_token:
            break
        if sampled_idx > 0:
            decoded_sentence.append(idx2word_hi[sampled_idx])
        target_seq[0,0] = sampled_idx

    return " ".join(decoded_sentence)

# Example usage
sentence = "Hello, how are you?"
input_seq = preprocess_input(sentence, tokenizer_en.word_index, max_seq_len=40)
translation = decode_sequence(input_seq, encoder_model, decoder_model, tokenizer_hi.word_index, tokenizer_hi.index_word, max_seq_len=40)
print("Predicted Hindi Translation:", translation)