Upload 7 files

.gitattributes

@@ -0,0 +1 @@
+Semiconductors.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Assessment3
+emoji: 👩🏼‍💻
+colorFrom: green
+colorTo: gray
+sdk: gradio
+sdk_version: 4.8.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Semiconductors.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1adbf493d65309de9821c550e8456a9a0940623357b509ae19ef0345fe1e0a
+size 2469240

app.py

@@ -0,0 +1,77 @@
+# https://huggingface.co/spaces/itsmariamaraki/AAI-Assessment3
+
+# Here are the imports
+
+import gradio as gr
+import PyPDF2
+from PyPDF2 import PdfReader
+from pdfminer.high_level import extract_pages, extract_text
+from transformers import pipeline, AutoProcessor, AutoModel, AutoTokenizer
+import torch
+import soundfile as sf
+from IPython.display import Audio
+from datasets import load_dataset
+from io import BytesIO
+import os
+
+# Here is the code
+
+def abstract(pdf_file):
+    pdf_bytes = BytesIO(pdf_file)
+    pdf_reader = PyPDF2.PdfReader(pdf_bytes)
+    
+    abstract = ''
+    
+    for page_number in range(len(pdf_reader.pages)):
+        text = pdf_reader.pages[page_number].extract_text()
+        
+        if 'abstract' in text.lower(): #in order to read only the abstract, i set as a start the abstract point & as an end the introduction point
+            start_index = text.lower().find('abstract')  
+            end_index = text.lower().find('introduction')
+            abstract = text[start_index:end_index]
+            break
+    
+    return abstract
+
+
+
+summarization = pipeline('summarization', model = 'pszemraj/long-t5-tglobal-base-16384-book-summary') #best summarization model i tested regarding this assessment
+audiospeech = pipeline('text-to-speech', model = 'suno/bark-small') #the voice is a bit distorted but gives a good output & takes less time
+
+
+
+def summarization_n_audiospeech(pdf_file):
+    abstract_text = abstract(pdf_file)
+
+    summary = summarization(abstract_text, max_length=50, min_length=10)[0]['summary_text'] #didn't know exactly what would give one sentence, so i checked multiple times the min & max lengths regarding the 11th article. for a dif article, those parameters would probably have to be different as well
+          
+    fin_summary = summary.split('.')[0] + '.' #extract and print only the first sentence of the summary
+
+    #converting the summarization into an audio output
+    tts_output = audiospeech(fin_summary)
+    audio_data = tts_output['audio'][0]
+    
+    with BytesIO() as buffer:
+        sf.write(buffer, audio_data, 16000, format = 'wav')
+        audio_bytes = buffer.getvalue()
+
+    return fin_summary, audio_bytes
+
+
+
+iface = gr.Interface(
+    fn = summarization_n_audiospeech,
+    inputs = gr.File(label='upload PDF', type='binary'), #if i didn't set a type, the gradio output was an error -  searched it online for the solution
+    outputs = [
+        gr.Textbox(label='Summarization of the Abstract:'), 
+        gr.Audio(label="Audio Speech of the Abstract's Summary:")
+        ],
+    title = "PDF's Abstract Summarization & Audio Speech Processor",
+    description = "App that generates a one-line summary of the abstract & a speech audio of this summarization -- requirements: app only accepts PDFs which include an ABSTRACT section",
+        examples = [os.path.join(os.path.dirname(__file__),  'Hidden_Technical_Debt.pdf'), 
+                os.path.join(os.path.dirname(__file__),  'Semiconductors.pdf'), 
+                os.path.join(os.path.dirname(__file__),  'Efficient_Estimation_of_Word_Representations.pdf') 
+               ]
+)
+
+iface.launch()

gitattributes

@@ -0,0 +1,42 @@
+*.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
+Article[[:space:]]6[[:space:]]BloombergGPT_[[:space:]]A[[:space:]]Large[[:space:]]Language[[:space:]]Model[[:space:]]for[[:space:]]Finance.pdf filter=lfs diff=lfs merge=lfs -text
+BloombergGPT.pdf filter=lfs diff=lfs merge=lfs -text
+Article[[:space:]]8[[:space:]]Llama[[:space:]]2_[[:space:]]Open[[:space:]]Foundation[[:space:]]and[[:space:]]Fine-Tuned[[:space:]]Chat[[:space:]]Models.pdf filter=lfs diff=lfs merge=lfs -text
+Llama_2.pdf filter=lfs diff=lfs merge=lfs -text
+Article[[:space:]]10[[:space:]]The[[:space:]]Future[[:space:]]of[[:space:]]AI[[:space:]]is[[:space:]]Hybrid.pdf filter=lfs diff=lfs merge=lfs -text
+The_Future_of_AI_is_Hybrid.pdf filter=lfs diff=lfs merge=lfs -text
+Semiconductors.pdf filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,12 @@
+transformers 
+PyPDF2 
+torch 
+torchaudio 
+pdfplumber 
+pdfminer.six 
+datasets 
+sentencepiece 
+gradio 
+soundfile 
+Ipython 
+numpy