The_AI

app.py

@@ -1,17 +1,28 @@
 import streamlit as st
-from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import T5ForConditionalGeneration, T5Tokenizer, pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
 import nltk
 from youtube_transcript_api import YouTubeTranscriptApi
 
 # Download NLTK data
 nltk.download('punkt')
 
-# Initialize the image captioning pipeline
+# Load models and tokenizers
+summary_model_name = 'utrobinmv/t5_summary_en_ru_zh_base_2048'
+summary_model = T5ForConditionalGeneration.from_pretrained(summary_model_name)
+summary_tokenizer = T5Tokenizer.from_pretrained(summary_model_name)
+
+tag_tokenizer = AutoTokenizer.from_pretrained("fabiochiu/t5-base-tag-generation")
+tag_model = AutoModelForSeq2SeqLM.from_pretrained("fabiochiu/t5-base-tag-generation")
+
 captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
-# Load the tokenizer and model for tag generation
-tokenizer = AutoTokenizer.from_pretrained("fabiochiu/t5-base-tag-generation")
-model = AutoModelForSeq2SeqLM.from_pretrained("fabiochiu/t5-base-tag-generation")
+# Function to summarize text
+def summarize_text(text, prefix):
+ src_text = prefix + text
+ input_ids = summary_tokenizer(src_text, return_tensors="pt")
+ generated_tokens = summary_model.generate(**input_ids)
+ result = summary_tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+ return result[0]
 
 # Function to fetch YouTube transcript
 def fetch_transcript(url):
@@ -27,32 +38,38 @@ def fetch_transcript(url):
 st.title("Multi-purpose Machine Learning App: WAVE_AI")
 
 # Create tabs for different functionalities
-tab1, tab2, tab3 = st.tabs(["Text Tag Generation", "Image Captioning", "YouTube Transcript"])
+tab1, tab2, tab3, tab4 = st.tabs(["Text Summarization", "Text Tag Generation", "Image Captioning", "YouTube Transcript"])
 
-# Image Captioning Tab
+# Text Summarization Tab
 with tab1:
+ st.header("Text Summarization")
+
+ input_text = st.text_area("Enter the text to summarize:", height=300)
+
+ if st.button("Generate Summaries"):
+ if input_text:
+ title1 = summarize_text(input_text, 'summary: ')
+ title2 = summarize_text(input_text, 'summary brief: ')
+ st.write("### Title 1")
+ st.write(title1)
+ st.write("### Title 2")
+ st.write(title2)
+ else:
+ st.warning("Please enter some text to summarize.")
+
+# Text Tag Generation Tab
+with tab2:
  st.header("Text Tag Generation")
  
- # Text area for user input
  text = st.text_area("Enter the text for tag extraction:", height=200)
  
- # Button to generate tags
  if st.button("Generate Tags"):
  if text:
  try:
- # Tokenize and encode the input text
- inputs = tokenizer([text], max_length=512, truncation=True, return_tensors="pt")
- 
- # Generate tags
- output = model.generate(**inputs, num_beams=8, do_sample=True, min_length=10, max_length=64)
- 
- # Decode the output
- decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
- 
- # Extract unique tags
+ inputs = tag_tokenizer([text], max_length=512, truncation=True, return_tensors="pt")
+ output = tag_model.generate(**inputs, num_beams=8, do_sample=True, min_length=10, max_length=64)
+ decoded_output = tag_tokenizer.batch_decode(output, skip_special_tokens=True)[0]
  tags = list(set(decoded_output.strip().split(", ")))
- 
- # Display the tags
  st.write("**Generated Tags:**")
  st.write(tags)
  except Exception as e:
@@ -60,36 +77,27 @@ with tab1:
  else:
  st.warning("Please enter some text to generate tags.")
 
-# Text Tag Generation Tab
-with tab2:
+# Image Captioning Tab
+with tab3:
  st.header("Image Captioning Extractor")
  
- # Input for image URL
  image_url = st.text_input("Enter the URL of the image:")
  
- # If an image URL is provided
  if image_url:
  try:
- # Display the image
  st.image(image_url, caption="Provided Image", use_column_width=True)
- 
- # Generate the caption
  caption = captioner(image_url)
- 
- # Display the caption
  st.write("**Generated Caption:**")
  st.write(caption[0]['generated_text'])
  except Exception as e:
  st.error(f"An error occurred: {e}")
 
 # YouTube Transcript Tab
-with tab3:
+with tab4:
  st.header("YouTube Video Transcript Extractor")
  
- # Input for YouTube URL
  youtube_url = st.text_input("Enter YouTube URL:")
  
- # Button to get transcript
  if st.button("Get Transcript"):
  if youtube_url:
  transcript = fetch_transcript(youtube_url)