Create app.py

app.py

@@ -0,0 +1,113 @@
+import json
+import numpy as np
+import tensorflow as tf
+from tensorflow import keras
+
+from huggingface_hub import from_pretrained_keras
+
+import gradio as gr
+
+latent_dim = 256
+num_encoder_tokens = 71
+max_encoder_seq_length = 15
+num_decoder_tokens = 92
+max_decoder_seq_length = 59
+
+with open("input_vocab.json", "r", encoding="utf-8") as f:
+    input_token_index = json.load(f)
+with open("target_vocab.json", "r", encoding="utf-8") as f:
+    target_token_index = json.load(f)
+
+model = from_pretrained_keras("keras-io/char-lstm-seq2seq")
+
+# Define sampling models
+# Restore the model and construct the encoder and decoder.
+
+encoder_inputs = model.input[0]  # input_1
+encoder_outputs, state_h_enc, state_c_enc = model.layers[2].output  # lstm_1
+encoder_states = [state_h_enc, state_c_enc]
+encoder_model = keras.Model(encoder_inputs, encoder_states)
+
+decoder_inputs = model.input[1]  # input_2
+decoder_state_input_h = keras.Input(shape=(latent_dim,), name="input_3")
+decoder_state_input_c = keras.Input(shape=(latent_dim,), name="input_4")
+decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
+decoder_lstm = model.layers[3]
+decoder_outputs, state_h_dec, state_c_dec = decoder_lstm(
+    decoder_inputs, initial_state=decoder_states_inputs
+)
+decoder_states = [state_h_dec, state_c_dec]
+decoder_dense = model.layers[4]
+decoder_outputs = decoder_dense(decoder_outputs)
+
+decoder_model = keras.Model(
+    [decoder_inputs] + decoder_states_inputs, [decoder_outputs] + decoder_states
+)
+
+# Reverse-lookup token index to decode sequences back to
+# something readable.
+reverse_input_char_index = dict((i, char) for char, i in input_token_index.items())
+reverse_target_char_index = dict((i, char) for char, i in target_token_index.items())
+
+
+def decode_sequence(input_seq):
+    # Encode the input as state vectors.
+    states_value = encoder_model.predict(input_seq)
+
+    # Generate empty target sequence of length 1.
+    target_seq = np.zeros((1, 1, num_decoder_tokens))
+    # Populate the first character of target sequence with the start character.
+    target_seq[0, 0, target_token_index["\t"]] = 1.0
+
+    # Sampling loop for a batch of sequences
+    # (to simplify, here we assume a batch of size 1).
+    stop_condition = False
+    decoded_sentence = ""
+    while not stop_condition:
+        output_tokens, h, c = decoder_model.predict([target_seq] + states_value)
+
+        # Sample a token
+        sampled_token_index = np.argmax(output_tokens[0, -1, :])
+        sampled_char = reverse_target_char_index[sampled_token_index]
+        decoded_sentence += sampled_char
+
+        # Exit condition: either hit max length
+        # or find stop character.
+        if sampled_char == "\n" or len(decoded_sentence) > max_decoder_seq_length:
+            stop_condition = True
+
+        # Update the target sequence (of length 1).
+        target_seq = np.zeros((1, 1, num_decoder_tokens))
+        target_seq[0, 0, sampled_token_index] = 1.0
+
+        # Update states
+        states_value = [h, c]
+    return decoded_sentence
+
+
+def translate(input_text):
+    encoder_input_data = np.zeros(
+        (1, max_encoder_seq_length, num_encoder_tokens), dtype="float32"
+    )
+    for t, char in enumerate(input_text):
+        encoder_input_data[0, t, input_token_index[char]] = 1.0
+    encoder_input_data[0, t + 1 :, input_token_index[" "]] = 1.0
+    target_text = decode_sequence(encoder_input_data)
+    return target_text
+
+
+input_box = gr.inputs.Textbox(type="str", label="Input Text")
+target = gr.outputs.Textbox()
+
+iface = gr.Interface(
+    translate,
+    input_box,
+    target,
+    title="Character-level recurrent sequence-to-sequence model",
+    description="Model for Translating English to French using a Character-level recurrent sequence-to-sequence trained with small data.",
+    article='Author: <a href="https://huggingface.co/anuragshas">Anurag Singh</a> . Based on the keras example from <a href="https://keras.io/examples/nlp/lstm_seq2seq//">fchollet</a>',
+    examples=["Hi.", "Wait!", "Go on."],
+)
+
+
+iface.launch()