Spaces:
Sleeping
Sleeping
| # https://huggingface.co/spaces/yilmazmusa_ml/abstract_summarizer | |
| # Here are the imports | |
| import warnings | |
| import pdfplumber | |
| import torch | |
| from transformers import pipeline, AutoProcessor, AutoModel | |
| import numpy as np | |
| import gradio as gr | |
| from scipy.io.wavfile import write as write_wav | |
| warnings.filterwarnings("ignore") | |
| # Here is the code | |
| def extract_abstract(uploaded_file): | |
| with pdfplumber.open(pdf_bytes) as pdf: | |
| abstract = "" | |
| # Iterate through each page | |
| for page in pdf.pages: | |
| text = page.extract_text(x_tolerance = 1, y_tolerance = 1) # these parameters are set 1 in order to get spaces between words and lines | |
| # Search for the "Abstract" keyword | |
| if "abstract" in text.lower(): | |
| # Found the "Abstract" keyword | |
| start_index = text.lower().find("abstract") # find the "abstract" title as starter index | |
| end_index = text.lower().find("introduction") # find the "introduction" title as end index | |
| abstract = text[start_index:end_index] | |
| break | |
| print(abstract) | |
| return abstract | |
| def process_summary(summary): | |
| # Split the summary by the first period | |
| summary = summary[0]["summary_text"] | |
| sentences = summary.split('.', 1) | |
| if len(sentences) > 0: | |
| # Retrieve the first part before the period | |
| processed_summary = sentences[0].strip() + "." | |
| # Replace "-" with an empty string | |
| processed_summary = processed_summary.replace("-", "") | |
| return processed_summary | |
| # Function for summarization and audio conversion | |
| def summarize_and_convert_to_audio(pdf_file): | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| print(device) | |
| # Move models and related tensors to CUDA device if available | |
| processor = AutoProcessor.from_pretrained("suno/bark") | |
| model = AutoModel.from_pretrained("suno/bark").to(device) | |
| # Extract abstract | |
| abstract_text = extract_abstract(pdf_file) | |
| if not abstract_text: | |
| return "No 'abstract' section found in the uploaded PDF. Please upload a different PDF." | |
| # Summarize the abstract | |
| summarization_pipeline = pipeline(task='summarization', model='knkarthick/MEETING_SUMMARY', min_length=15, max_length=30) | |
| summarized_text = summarization_pipeline(abstract_text) | |
| one_sentence_summary = process_summary(summarized_text) | |
| print(one_sentence_summary) | |
| # Text-to-audio conversion | |
| inputs = processor( | |
| text=[one_sentence_summary], | |
| return_tensors="pt", | |
| ) | |
| inputs = inputs.to(device) | |
| speech_values = model.generate(**inputs, do_sample=True) | |
| sampling_rate = model.generation_config.sample_rate | |
| # Convert speech values to audio data | |
| audio_data = speech_values.cpu().numpy().squeeze() | |
| # Convert audio data to bytes | |
| with BytesIO() as buffer: | |
| write_wav(buffer, sampling_rate, audio_data.astype(np.float32)) | |
| audio_bytes = buffer.getvalue() | |
| return audio_bytes, sampling_rate # Return audio as bytes with sampling rate | |
| # Create a Gradio interface | |
| iface = gr.Interface( | |
| fn=summarize_and_convert_to_audio, | |
| inputs=gr.UploadButton(label="Upload PDF", type="filepath", file_types=["pdf"]), # Set to accept only PDF files | |
| outputs=gr.Audio(label="Audio"), | |
| title="PDF Abstract Summarizer", | |
| description="Upload a PDF with an abstract to generate a summarized audio." | |
| ) | |
| iface.launch() |