Spaces:
Sleeping
Sleeping
sahibnanda
commited on
Commit
•
d9579cb
1
Parent(s):
48ec1cf
commit
Browse files- TextSummarizationModel/assets/tokenizer/merges.txt +0 -0
- TextSummarizationModel/assets/tokenizer/vocabulary.json +0 -0
- TextSummarizationModel/config.json +1 -0
- TextSummarizationModel/metadata.json +6 -0
- TextSummarizationModel/model.weights.h5 +3 -0
- TextSummarizationModel/new_model.weights.h5 +3 -0
- TextSummarizationModel/tokenizer.json +17 -0
- app.py +53 -0
- requirements.txt +6 -0
- textSFunctionality.py +27 -0
TextSummarizationModel/assets/tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
TextSummarizationModel/assets/tokenizer/vocabulary.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
TextSummarizationModel/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"keras_version": "3.0.1",
|
3 |
+
"keras_nlp_version": "0.7.0",
|
4 |
+
"parameter_count": 139417344,
|
5 |
+
"date_saved": "2023-12-27@02:00:52"
|
6 |
+
}
|
TextSummarizationModel/model.weights.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab4030711d47cbed4fd3f8fe913977aef6e4932f0f05d5bba91e2de066e08f1f
|
3 |
+
size 558205584
|
TextSummarizationModel/new_model.weights.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b8c98bd0559fd313c22c7a16c9109053fb1aacea38c0b514486fb441ad0b0d
|
3 |
+
size 1673753584
|
TextSummarizationModel/tokenizer.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"module": "keras_nlp.src.models.bart.bart_tokenizer",
|
3 |
+
"class_name": "BartTokenizer",
|
4 |
+
"config": {
|
5 |
+
"name": "bart_tokenizer",
|
6 |
+
"trainable": true,
|
7 |
+
"dtype": "int32",
|
8 |
+
"sequence_length": null,
|
9 |
+
"add_prefix_space": false
|
10 |
+
},
|
11 |
+
"registered_name": "keras_nlp>BartTokenizer",
|
12 |
+
"assets": [
|
13 |
+
"assets/tokenizer/merges.txt",
|
14 |
+
"assets/tokenizer/vocabulary.json"
|
15 |
+
],
|
16 |
+
"weights": null
|
17 |
+
}
|
app.py
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from textSFunctionality import generateText
|
3 |
+
|
4 |
+
# Set the page configuration and theme once at the top
|
5 |
+
st.set_page_config(page_title="Text Summarization", page_icon="⭐")
|
6 |
+
|
7 |
+
st.write(
|
8 |
+
"""
|
9 |
+
<style>
|
10 |
+
.reportview-container {
|
11 |
+
background-color: #f8f9fa;
|
12 |
+
}
|
13 |
+
.sidebar .sidebar-content {
|
14 |
+
background-color: #f0f2f6;
|
15 |
+
}
|
16 |
+
h1 {
|
17 |
+
color: #0cdec0;
|
18 |
+
}
|
19 |
+
.stButton > button {
|
20 |
+
background-color: #38d6c0; /* Lighter teal shade */
|
21 |
+
color: black;
|
22 |
+
font-weight: bold;
|
23 |
+
transition: background-color 0.3s, color 0.3s;
|
24 |
+
}
|
25 |
+
.stButton > button:hover {
|
26 |
+
background-color: #01947f; /* Even lighter teal for hover */
|
27 |
+
color: white; /* Change text color on hover */
|
28 |
+
}
|
29 |
+
.stTextArea > textarea {
|
30 |
+
background-color: #ffffff;
|
31 |
+
color: #333;
|
32 |
+
}
|
33 |
+
</style>
|
34 |
+
""", unsafe_allow_html=True
|
35 |
+
)
|
36 |
+
|
37 |
+
def main():
|
38 |
+
st.title('Text Summarization')
|
39 |
+
|
40 |
+
# Text area for user input
|
41 |
+
user_input = st.text_area("#### **Enter Text To Summarize**:", height=300)
|
42 |
+
|
43 |
+
# Button to trigger summarization
|
44 |
+
if st.button("Summarize"):
|
45 |
+
if user_input:
|
46 |
+
summary = generateText(user_input)
|
47 |
+
st.write("#### **Summarized Text**:")
|
48 |
+
st.write(summary)
|
49 |
+
else:
|
50 |
+
st.write("Please Enter Some Text To Summarize.")
|
51 |
+
|
52 |
+
if __name__ == '__main__':
|
53 |
+
main()
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
streamlit==1.33.0
|
2 |
+
numpy==1.26.4
|
3 |
+
keras==2.15.0
|
4 |
+
tensorflow==2.15.0
|
5 |
+
tensorflow-text==2.15.0
|
6 |
+
keras-nlp==0.9.3
|
textSFunctionality.py
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import os
|
3 |
+
import tensorflow as tf
|
4 |
+
import keras
|
5 |
+
import keras_nlp
|
6 |
+
|
7 |
+
MAX_ENCODER_SEQUENCE_LENGTH = 512
|
8 |
+
MAX_DECODER_SEQUENCE_LENGTH = 128
|
9 |
+
|
10 |
+
MODEL_PATH = r"TextSummarizationModel"
|
11 |
+
WEIGHT_PATH = r"new_model.weights.h5"
|
12 |
+
WEIGHT_PATH = os.path.join(MODEL_PATH, WEIGHT_PATH)
|
13 |
+
|
14 |
+
def cleanText(text):
|
15 |
+
text = str(text)
|
16 |
+
text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
|
17 |
+
text = text.lower()
|
18 |
+
return text
|
19 |
+
|
20 |
+
preprocessor = keras_nlp.models.BartSeq2SeqLMPreprocessor.from_preset(MODEL_PATH, encoder_sequence_length=MAX_ENCODER_SEQUENCE_LENGTH,decoder_sequence_length=MAX_DECODER_SEQUENCE_LENGTH,)
|
21 |
+
model = keras_nlp.models.BartSeq2SeqLM.from_preset(MODEL_PATH, preprocessor=preprocessor)
|
22 |
+
model.load_weights(WEIGHT_PATH)
|
23 |
+
|
24 |
+
def generateText(input_text, model=model, max_length=200):
|
25 |
+
input_text = cleanText(input_text)
|
26 |
+
output = model.generate(input_text, max_length=max_length)
|
27 |
+
return output
|