commit

TextSummarizationModel/config.json

@@ -0,0 +1 @@
+{"module": "keras_nlp.src.models.bart.bart_backbone", "class_name": "BartBackbone", "config": {"name": "bart_backbone", "trainable": true, "vocabulary_size": 50265, "num_layers": 6, "num_heads": 12, "hidden_dim": 768, "intermediate_dim": 3072, "dropout": 0.1, "max_sequence_length": 1024}, "registered_name": "keras_nlp>BartBackbone", "build_config": {"input_shape": {"encoder_token_ids": [null, null], "encoder_padding_mask": [null, null], "decoder_token_ids": [null, null], "decoder_padding_mask": [null, null]}}, "weights": "model.weights.h5"}

TextSummarizationModel/metadata.json

@@ -0,0 +1,6 @@
+{
+    "keras_version": "3.0.1",
+    "keras_nlp_version": "0.7.0",
+    "parameter_count": 139417344,
+    "date_saved": "2023-12-27@02:00:52"
+}

TextSummarizationModel/model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4030711d47cbed4fd3f8fe913977aef6e4932f0f05d5bba91e2de066e08f1f
+size 558205584

TextSummarizationModel/new_model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b8c98bd0559fd313c22c7a16c9109053fb1aacea38c0b514486fb441ad0b0d
+size 1673753584

TextSummarizationModel/tokenizer.json

@@ -0,0 +1,17 @@
+{
+    "module": "keras_nlp.src.models.bart.bart_tokenizer",
+    "class_name": "BartTokenizer",
+    "config": {
+        "name": "bart_tokenizer",
+        "trainable": true,
+        "dtype": "int32",
+        "sequence_length": null,
+        "add_prefix_space": false
+    },
+    "registered_name": "keras_nlp>BartTokenizer",
+    "assets": [
+        "assets/tokenizer/merges.txt",
+        "assets/tokenizer/vocabulary.json"
+    ],
+    "weights": null
+}

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from textSFunctionality import generateText
+
+# Set the page configuration and theme once at the top
+st.set_page_config(page_title="Text Summarization", page_icon="⭐")
+
+st.write(
+    """
+    <style>
+    .reportview-container {
+        background-color: #f8f9fa;
+    }
+    .sidebar .sidebar-content {
+        background-color: #f0f2f6;
+    }
+    h1 {
+        color: #0cdec0;
+    }
+    .stButton > button {
+        background-color: #38d6c0; /* Lighter teal shade */
+        color: black;
+        font-weight: bold;
+        transition: background-color 0.3s, color 0.3s;
+    }
+    .stButton > button:hover {
+        background-color: #01947f; /* Even lighter teal for hover */
+        color: white; /* Change text color on hover */
+    }
+    .stTextArea > textarea {
+        background-color: #ffffff;
+        color: #333;
+    }
+    </style>
+    """, unsafe_allow_html=True
+)
+
+def main():
+    st.title('Text Summarization')
+
+    # Text area for user input
+    user_input = st.text_area("#### **Enter Text To Summarize**:", height=300)
+
+    # Button to trigger summarization
+    if st.button("Summarize"):
+        if user_input:
+            summary = generateText(user_input)
+            st.write("#### **Summarized Text**:")
+            st.write(summary)
+        else:
+            st.write("Please Enter Some Text To Summarize.")
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,6 @@
+streamlit==1.33.0
+numpy==1.26.4
+keras==2.15.0
+tensorflow==2.15.0
+tensorflow-text==2.15.0
+keras-nlp==0.9.3

textSFunctionality.py

@@ -0,0 +1,27 @@
+import re
+import os
+import tensorflow as tf
+import keras
+import keras_nlp
+
+MAX_ENCODER_SEQUENCE_LENGTH = 512
+MAX_DECODER_SEQUENCE_LENGTH = 128
+
+MODEL_PATH = r"TextSummarizationModel"
+WEIGHT_PATH = r"new_model.weights.h5"
+WEIGHT_PATH = os.path.join(MODEL_PATH, WEIGHT_PATH)
+
+def cleanText(text):
+    text = str(text)
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    text = text.lower()
+    return text
+
+preprocessor = keras_nlp.models.BartSeq2SeqLMPreprocessor.from_preset(MODEL_PATH, encoder_sequence_length=MAX_ENCODER_SEQUENCE_LENGTH,decoder_sequence_length=MAX_DECODER_SEQUENCE_LENGTH,)
+model = keras_nlp.models.BartSeq2SeqLM.from_preset(MODEL_PATH, preprocessor=preprocessor)
+model.load_weights(WEIGHT_PATH)
+
+def generateText(input_text, model=model, max_length=200):
+    input_text = cleanText(input_text)
+    output = model.generate(input_text, max_length=max_length)
+    return output