Abstract Text Summarizer

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,20 @@
+# Use the official Python image from the Docker Hub
+FROM python:3.10.0-slim-buster
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Make port 7860 available to the world outside this container
+EXPOSE 7860
+
+# Define environment variable (corrected the syntax for environment variable name and value)
+# ENV FLASK_APP=app.py
+
+# Command to run the application
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]

README.md

@@ -1,11 +1,11 @@
----
-title: Abstract Text Summarizer
-emoji: 🔥
-colorFrom: indigo
-colorTo: green
-sdk: docker
-pinned: false
-license: cc-by-nc-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Abstract Text Summarizer
+emoji: 🔥
+colorFrom: indigo
+colorTo: green
+sdk: docker
+pinned: false
+license: cc-by-nc-3.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,84 @@
+from flask import Flask, request, render_template, jsonify
+import re
+import nltk
+import torch
+from pathlib import Path
+
+# Define the device if using GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+from transformers import pipeline
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+
+nltk.download('punkt')
+nltk.download('wordnet')
+
+app = Flask(__name__)
+
+tokenizer = AutoTokenizer.from_pretrained(Path("summary/tokenizer"))
+model_name = "summary/pegasus-samsum-model"
+
+def remove_spaces_before_punctuation(text):
+    pattern = re.compile(r'(\s+)([.,;!?])')
+    result = pattern.sub(r'\2', text)
+    result = re.sub(r'\[|\]', '', result)
+    return result
+
+def replace_pronouns(text):
+    # Replace "they" with "he" or "she" based on context
+    text = re.sub(r'\bthey\b', 'He/She', text, flags=re.IGNORECASE)
+    text = re.sub(r'\b(are|have|were)\b', lambda x: {'are': 'is', 'have': 'has', 'were': 'was'}[x.group()], text)
+    return text
+
+def clean_and_lemmatize(text):
+    # Remove digits, symbols, punctuation marks, and newline characters
+    text = re.sub(r'\d+', '', text)
+    text = re.sub(r'[^\w\s,-]', '', text.replace('\n', ''))
+    # Tokenize the text
+    tokens = word_tokenize(text.lower())
+    # Initialize lemmatizer
+    lemmatizer = WordNetLemmatizer()
+    # Lemmatize each token and join back into a sentence
+    lemmatized_text = ' '.join([lemmatizer.lemmatize(token) for token in tokens])
+    return lemmatized_text
+
+@app.route('/summarize', methods=['POST'])
+def summarize():
+    # Get the input text from the request
+    input_text = request.form['input_text']
+    
+    # Tokenize the input text
+    tokens_org_text = tokenizer.tokenize(input_text)
+    sequence_length_org_text = len(tokens_org_text)
+
+    input_text = clean_and_lemmatize(input_text)
+    tokens = tokenizer.tokenize(input_text)
+    sequence_length = len(tokens)
+
+    if sequence_length >= 1024:
+        return jsonify({'error': 'Input text exceeds maximum token length of 1023.'})
+
+    # Initialize model variable
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name).to(device)
+    
+    gen_kwargs = {"length_penalty": 0.8, "num_beams": 8, "max_length": 128}
+    pipe = pipeline("summarization", model=model, tokenizer=tokenizer, device=device)
+    
+    text = pipe(input_text, **gen_kwargs)[0]["summary_text"]
+    output_text = replace_pronouns(remove_spaces_before_punctuation(text))
+    
+    # Clear the GPU cache
+    torch.cuda.empty_cache()
+    
+    # Return the summary
+    return jsonify({'summary': output_text})
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', debug=True, port=7860) # This is Host Port
+

main.py

@@ -0,0 +1,83 @@
+# python == 3.11.7
+
+import re
+import nltk
+import torch
+from pathlib import Path
+# Define the device if using GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+from transformers import pipeline
+# from transformers import AutoTokenizer
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+nltk.download('punkt')
+nltk.download('wordnet')
+
+tokenizer = AutoTokenizer.from_pretrained(Path("summary/tokenizer"))
+model = "summary/pegasus-samsum-model"
+def remove_spaces_before_punctuation(text):
+    pattern = re.compile(r'(\s+)([.,;!?])')
+    result = pattern.sub(r'\2', text)
+    result = re.sub(r'\[|\]', '', result)
+    return result
+
+
+def replace_pronouns(text):
+    # Replace "they" with "he" or "she" based on context
+    text = re.sub(r'\bthey\b', 'He/She', text, flags=re.IGNORECASE)
+    text = re.sub(r'\b(are|have|were)\b', lambda x: {'are': 'is', 'have': 'has', 'were': 'was'}[x.group()], text)
+    return text
+
+
+def clean_and_lemmatize(text):
+    # Remove digits, symbols, punctuation marks, and newline characters
+    text = re.sub(r'\d+', '', text)
+    text = re.sub(r'[^\w\s,-]', '', text.replace('\n', ''))
+    # Tokenize the text
+    tokens = word_tokenize(text.lower())
+    # Initialize lemmatizer
+    lemmatizer = WordNetLemmatizer()
+    # Lemmatize each token and join back into a sentence
+    lemmatized_text = ' '.join([lemmatizer.lemmatize(token) for token in tokens])
+    return lemmatized_text
+
+
+# input_text = input("\nGive me Your Full Month Log hour Task Description within 5500 Characters: \n")
+input_text = """
+['investigate feedback for eb app add task, meeting, and call log in lead show task, meeting, and call log from lead show lead and call log from account detail add lead, call log, and meeting from account detail crt screen fix bug in adding lead from account test and fix attendance in eb app rd business card scanner in eb app fix email issue in call detail add account in dm and lead list rd on business card scanner meeting on eb app feedback fix bug in lead add add image cropper in card scanner change attendance ui fix attendance design and fix activity log add selected item bug add filter in colleague screen and fix activity add task offspring add vendor address in colleague list investigate all colleague list not found issue add vendor address in colleague list jam all colleague not issue add month stepper attendance add month picker in attendance fix loading problem in monthly attendance on phone number format rd daily activity setup laptop for flutter development change phone number format algorithm fix loading issue in daily attendance screen add daily activity summary design profile screen change design in detail screen release build aab reload contact colleague and account using refresh indicator add doughnut for attendance percent meeting on eb app not found issue in play store add address for partner in colleague list and change dashboard order designation in colleague and contact call detail move favorite button position and phone state stream bug eb app feedback collection and analysis change search algorithm add contact share feature build aab for play store meeting with md sir on new requirement check in for eb app papers requirement for check in feature share contact using or vcard build aab for play store save contact analyze check in feature in eb sort client by name or time sort account by name and time add notice, my team, and favorite in home screen sort colleague by name or update time fix search issue in colleague disable icon if phone or email not found in contact detail page share and save colleague phone and email add time and in meeting detail fix app close issue when permission is denied fix favorite height issue fix design issue fix design in attendance screen meeting with md sir on check - in feature show device name in contact modify filter in colleague design fix add monthly lumber hour pie chart rd on theme in flutter to change default color of button fix device call log issue design and bug fixing fix issue in disabling email icon and fix issue in device contact name show integrate favorite add api sync favorite with server design and bug fixing change monthly activity graph fix bug in opt timer show colleague image from eb profile pic bug fixing in lead add show people image in contact list and call detail compute attendance work hour design fix document api for business card upload study wetucom rd']
+
+"""
+
+# Tokenize the input text
+tokens_org_text = tokenizer.tokenize(input_text)
+# print(tokens_org_text)
+# Get the length of the tokenized sequence
+sequence_length_org_text = len(tokens_org_text)
+
+# print(sequence_length_org_text)
+
+input_text = clean_and_lemmatize(input_text)
+# Tokenize the input text
+tokens = tokenizer.tokenize(input_text)
+
+# Get the length of the tokenized sequence
+sequence_length = len(tokens)
+# print(sequence_length)
+
+
+if sequence_length >= 1024:
+    print(f"Your Text token length is {sequence_length_org_text} Which exceeds 1023 tokens")
+else:
+    model = AutoModelForSeq2SeqLM.from_pretrained(model).to(device)
+   
+    gen_kwargs = {"length_penalty": 0.8, "num_beams": 8, "max_length": 128}
+
+    pipe = pipeline("summarization", model=model, tokenizer=tokenizer, device=device)
+    # Example usage
+    text = pipe(input_text, **gen_kwargs)[0]["summary_text"]
+    output_text = replace_pronouns(remove_spaces_before_punctuation(text))
+    print("Summary: ", output_text)
+    # Clear the GPU cache
+    torch.cuda.empty_cache()

requirements.txt

@@ -0,0 +1,5 @@
+transformers == 4.36.0
+torch == 2.1.1
+nltk ==3.8.1
+flask
+gunicorn

summary/pegasus-samsum-model/config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "google/pegasus-cnn_dailymail",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "PegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 0,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 1,
+  "forced_eos_token_id": 1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "max_position_embeddings": 1024,
+  "min_length": 32,
+  "model_type": "pegasus",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 96103
+}

summary/pegasus-samsum-model/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "min_length": 32,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

summary/pegasus-samsum-model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c19d3029852ef26b0859301c6793ebfb3d00905438f4cccd5844c41507e6ed
+size 2283652852

summary/tokenizer/special_tokens_map.json

@@ -0,0 +1,110 @@
+{
+  "additional_special_tokens": [
+    "<mask_1>",
+    "<unk_2>",
+    "<unk_3>",
+    "<unk_4>",
+    "<unk_5>",
+    "<unk_6>",
+    "<unk_7>",
+    "<unk_8>",
+    "<unk_9>",
+    "<unk_10>",
+    "<unk_11>",
+    "<unk_12>",
+    "<unk_13>",
+    "<unk_14>",
+    "<unk_15>",
+    "<unk_16>",
+    "<unk_17>",
+    "<unk_18>",
+    "<unk_19>",
+    "<unk_20>",
+    "<unk_21>",
+    "<unk_22>",
+    "<unk_23>",
+    "<unk_24>",
+    "<unk_25>",
+    "<unk_26>",
+    "<unk_27>",
+    "<unk_28>",
+    "<unk_29>",
+    "<unk_30>",
+    "<unk_31>",
+    "<unk_32>",
+    "<unk_33>",
+    "<unk_34>",
+    "<unk_35>",
+    "<unk_36>",
+    "<unk_37>",
+    "<unk_38>",
+    "<unk_39>",
+    "<unk_40>",
+    "<unk_41>",
+    "<unk_42>",
+    "<unk_43>",
+    "<unk_44>",
+    "<unk_45>",
+    "<unk_46>",
+    "<unk_47>",
+    "<unk_48>",
+    "<unk_49>",
+    "<unk_50>",
+    "<unk_51>",
+    "<unk_52>",
+    "<unk_53>",
+    "<unk_54>",
+    "<unk_55>",
+    "<unk_56>",
+    "<unk_57>",
+    "<unk_58>",
+    "<unk_59>",
+    "<unk_60>",
+    "<unk_61>",
+    "<unk_62>",
+    "<unk_63>",
+    "<unk_64>",
+    "<unk_65>",
+    "<unk_66>",
+    "<unk_67>",
+    "<unk_68>",
+    "<unk_69>",
+    "<unk_70>",
+    "<unk_71>",
+    "<unk_72>",
+    "<unk_73>",
+    "<unk_74>",
+    "<unk_75>",
+    "<unk_76>",
+    "<unk_77>",
+    "<unk_78>",
+    "<unk_79>",
+    "<unk_80>",
+    "<unk_81>",
+    "<unk_82>",
+    "<unk_83>",
+    "<unk_84>",
+    "<unk_85>",
+    "<unk_86>",
+    "<unk_87>",
+    "<unk_88>",
+    "<unk_89>",
+    "<unk_90>",
+    "<unk_91>",
+    "<unk_92>",
+    "<unk_93>",
+    "<unk_94>",
+    "<unk_95>",
+    "<unk_96>",
+    "<unk_97>",
+    "<unk_98>",
+    "<unk_99>",
+    "<unk_100>",
+    "<unk_101>",
+    "<unk_102>"
+  ],
+  "eos_token": "</s>",
+  "mask_token": "<mask_2>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

summary/tokenizer/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
+size 1912529

summary/tokenizer/tokenizer_config.json

@@ -0,0 +1,967 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<mask_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<mask_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<unk_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<unk_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<unk_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<unk_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<unk_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<unk_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<unk_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<unk_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<unk_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<unk_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<unk_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<unk_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<unk_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<unk_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<unk_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<unk_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<unk_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<unk_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<unk_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<unk_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<unk_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<unk_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<unk_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<unk_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<unk_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<unk_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<unk_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<unk_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<unk_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<unk_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<unk_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<unk_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<unk_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<unk_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<unk_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "<unk_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "<unk_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<unk_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "<unk_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "<unk_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<unk_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<unk_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<unk_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<unk_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<unk_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "<unk_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "<unk_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "<unk_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<unk_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "<unk_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "<unk_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<unk_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "<unk_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<unk_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "<unk_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<unk_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "<unk_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<unk_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<unk_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "<unk_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<unk_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<unk_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "<unk_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<unk_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<unk_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "<unk_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<unk_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<unk_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "<unk_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<unk_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<unk_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "<unk_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<unk_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "78": {
+      "content": "<unk_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<unk_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<unk_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "<unk_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<unk_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "<unk_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84": {
+      "content": "<unk_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "content": "<unk_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<unk_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "87": {
+      "content": "<unk_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "content": "<unk_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "89": {
+      "content": "<unk_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<unk_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<unk_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "<unk_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "<unk_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "<unk_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<unk_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<unk_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "<unk_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "98": {
+      "content": "<unk_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99": {
+      "content": "<unk_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<unk_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<unk_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<unk_100>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<unk_101>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<unk_102>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<mask_1>",
+    "<unk_2>",
+    "<unk_3>",
+    "<unk_4>",
+    "<unk_5>",
+    "<unk_6>",
+    "<unk_7>",
+    "<unk_8>",
+    "<unk_9>",
+    "<unk_10>",
+    "<unk_11>",
+    "<unk_12>",
+    "<unk_13>",
+    "<unk_14>",
+    "<unk_15>",
+    "<unk_16>",
+    "<unk_17>",
+    "<unk_18>",
+    "<unk_19>",
+    "<unk_20>",
+    "<unk_21>",
+    "<unk_22>",
+    "<unk_23>",
+    "<unk_24>",
+    "<unk_25>",
+    "<unk_26>",
+    "<unk_27>",
+    "<unk_28>",
+    "<unk_29>",
+    "<unk_30>",
+    "<unk_31>",
+    "<unk_32>",
+    "<unk_33>",
+    "<unk_34>",
+    "<unk_35>",
+    "<unk_36>",
+    "<unk_37>",
+    "<unk_38>",
+    "<unk_39>",
+    "<unk_40>",
+    "<unk_41>",
+    "<unk_42>",
+    "<unk_43>",
+    "<unk_44>",
+    "<unk_45>",
+    "<unk_46>",
+    "<unk_47>",
+    "<unk_48>",
+    "<unk_49>",
+    "<unk_50>",
+    "<unk_51>",
+    "<unk_52>",
+    "<unk_53>",
+    "<unk_54>",
+    "<unk_55>",
+    "<unk_56>",
+    "<unk_57>",
+    "<unk_58>",
+    "<unk_59>",
+    "<unk_60>",
+    "<unk_61>",
+    "<unk_62>",
+    "<unk_63>",
+    "<unk_64>",
+    "<unk_65>",
+    "<unk_66>",
+    "<unk_67>",
+    "<unk_68>",
+    "<unk_69>",
+    "<unk_70>",
+    "<unk_71>",
+    "<unk_72>",
+    "<unk_73>",
+    "<unk_74>",
+    "<unk_75>",
+    "<unk_76>",
+    "<unk_77>",
+    "<unk_78>",
+    "<unk_79>",
+    "<unk_80>",
+    "<unk_81>",
+    "<unk_82>",
+    "<unk_83>",
+    "<unk_84>",
+    "<unk_85>",
+    "<unk_86>",
+    "<unk_87>",
+    "<unk_88>",
+    "<unk_89>",
+    "<unk_90>",
+    "<unk_91>",
+    "<unk_92>",
+    "<unk_93>",
+    "<unk_94>",
+    "<unk_95>",
+    "<unk_96>",
+    "<unk_97>",
+    "<unk_98>",
+    "<unk_99>",
+    "<unk_100>",
+    "<unk_101>",
+    "<unk_102>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": "<mask_2>",
+  "mask_token_sent": "<mask_1>",
+  "model_max_length": 1024,
+  "offset": 103,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PegasusTokenizer",
+  "unk_token": "<unk>"
+}

templates/index.html

@@ -0,0 +1,130 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Text Summarization</title>
+    <style>
+        body {
+            display: flex;
+            flex-direction: column;
+            justify-content: center;
+            align-items: center;
+            height: 100vh;
+            margin: 0;
+            background: url('static/Text-Summarization.jpg') no-repeat center center fixed;
+            background-size: cover;
+            font-family: Arial, sans-serif;
+            position: relative;
+        }
+
+        #content {
+            text-align: center;
+            background: rgba(255, 255, 255, 0.8); /* Semi-transparent background for better readability */
+            padding: 20px;
+            border-radius: 10px;
+        }
+
+        #summary {
+            margin-top: 20px;
+            color: black;
+            font-weight: bold;
+        }
+
+        #loading {
+            display: none;
+            color: green;
+        }
+
+        #input_text {
+            width: 80%; /* Adjust width as needed */
+            height: 200px; /* Adjust height as needed */
+            resize: vertical; /* Allow vertical resizing */
+            margin-top: 10px;
+            padding: 10px;
+            border-radius: 5px;
+            border: 1px solid #ccc;
+        }
+
+        button {
+            margin-top: 10px;
+            padding: 10px 20px;
+            background-color: #4CAF50;
+            color: white;
+            border: none;
+            border-radius: 5px;
+            cursor: pointer;
+        }
+
+        button:hover {
+            background-color: #45a049;
+        }
+
+        #logo {
+            position: absolute;
+            top: 20px;
+            right: 20px;
+            width: 150px; /* Adjust width as needed */
+        }
+
+        #footer {
+            position: absolute;
+            bottom: 10px;
+            text-align: center;
+            width: 100%;
+            color: white;
+        }
+    </style>
+</head>
+<body>
+    <div id="logo">
+        <img src="static/logo.png" alt="Logo" width="150"> <!-- Adjust width as needed -->
+    </div>
+    <div id="content">
+        <h1>Text Summarization</h1>
+        <form id="summarizeForm">
+            <label for="input_text">Enter text to summarize:</label><br>
+            <textarea id="input_text" name="input_text" rows="10" cols="50"></textarea><br>
+            <button type="submit">Summarize</button>
+        </form>
+        <div id="loading">Loading...</div>
+        <div id="summary"></div>
+    </div>
+    <div id="footer">
+        &copy; <span id="year"></span> Bikasuzzaman. Machine Learning Engineer.
+    </div>
+
+    <script src="https://code.jquery.com/jquery-3.6.0.min.js"></script>
+    <script>
+        $(document).ready(function () {
+            $('#summarizeForm').submit(function (event) {
+                event.preventDefault();
+                var formData = new FormData(this);
+                
+                // Show loading circle
+                $('#loading').show();
+                
+                $.ajax({
+                    type: 'POST',
+                    url: '/summarize',
+                    data: formData,
+                    processData: false,
+                    contentType: false,
+                    success: function (data) {
+                        $('#summary').text(data.summary);
+                        // Hide loading circle
+                        $('#loading').hide();
+                    },
+                    error: function () {
+                        alert('Error summarizing text.');
+                        // Hide loading circle
+                        $('#loading').hide();
+                    }
+                });
+            });
+
+            // Set the current year in the footer
+            const currentYear = new Date().getFullYear();
+            $('#year').text(currentYear);
+        });
+    </script>
+</body>
+</html>