ic

app.py

@@ -0,0 +1,101 @@
+# -*- coding: utf-8 -*-
+"""Copy of english model testing.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/13LT1keMRDkMSrOYjvzkneI_PaRnLQWl0
+"""
+
+!pip install gradio
+
+from nltk.corpus import stopwords
+import pandas as pd
+
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential, Model
+from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional, Input, GRU
+
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+import nltk
+import requests
+nltk.download('stopwords')
+nltk.download('wordnet')
+nltk.download('punkt')
+nltk.download('averaged_perceptron_tagger')
+
+eurl = 'https://raw.githubusercontent.com/sofiagiaccotto/newengpoemdatasetNLP/main/poems.txt'
+ans = requests.get(eurl)
+edf = ans.text
+
+tokenizer = Tokenizer()
+
+corpus = edf.lower().split("\n")
+
+tokenizer.fit_on_texts(corpus)
+total_words = len(tokenizer.word_index) + 1
+
+print(tokenizer.word_index)
+print(total_words)
+
+input_sequences = []
+for line in corpus:
+	token_list = tokenizer.texts_to_sequences([line])[0]
+	for i in range(1, len(token_list)):
+		n_gram_sequence = token_list[:i+1]
+		input_sequences.append(n_gram_sequence)
+
+# pad sequences
+max_sequence_len = max([len(x) for x in input_sequences])
+input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))
+
+# create predictors and label
+xs, labels = input_sequences[:,:-1],input_sequences[:,-1]
+
+ys = tf.keras.utils.to_categorical(labels, num_classes=total_words)
+
+import requests
+# URL of the model
+url = 'https://github.com/Obai33/NLP_PoemGenerationDatasets/raw/main/modeleng1.h5'
+# Local file path to save the model
+local_filename = 'modeleng1.h5'
+
+# Download the model file
+response = requests.get(url)
+with open(local_filename, 'wb') as f:
+    f.write(response.content)
+
+# Load the pre-trained model
+model = tf.keras.models.load_model(local_filename)
+
+def generate_english_text(seed_text, next_words=50):
+    generated_text = seed_text
+    for _ in range(next_words):
+        token_list = tokenizer.texts_to_sequences([generated_text])[0]
+        token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
+        predicted = np.argmax(model.predict(token_list), axis=-1)
+        output_word = ""
+        for word, index in tokenizer.word_index.items():
+          if index == predicted:
+            output_word = word
+            break
+        generated_text += " " + output_word
+    return generated_text
+
+import gradio as gr
+
+# Update Gradio interface to include both Arabic and English outputs
+iface = gr.Interface(
+    fn=generate_english_text,
+    inputs="text",
+    outputs="text",
+    title="English Poetry Generation",
+    description="Enter English text to generate a small poem.",
+    theme="compact"
+)
+# Run the interface
+iface.launch()