Create app.py

app.py

@@ -0,0 +1,86 @@
+#https://huggingface.co/spaces/Xuratron/abstract-speech-summarizer
+
+# Here are the imports
+import PyPDF2
+import re
+import torch
+from transformers import pipeline
+import soundfile as sf
+from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
+from fairseq.models.text_to_speech.hub_interface import TTSHubInterface
+import gradio as gr
+
+
+# Here is the code
+
+def extract_and_clean_abstract(uploaded_file):
+    """
+    Extracts and cleans the abstract from the uploaded PDF file.
+    """
+    reader = PyPDF2.PdfReader(uploaded_file.file)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text() or ""
+
+    # Regular expression pattern to find the abstract
+    pattern = r"(Abstract|ABSTRACT|abstract)(.*?)(Introduction|INTRODUCTION|introduction|1|Keywords|KEYWORDS|keywords)"
+    match = re.search(pattern, text, re.DOTALL)
+
+    if match:
+        abstract = match.group(2).strip()
+    else:
+        abstract = "Abstract not found."
+
+    # Clean the abstract text
+    cleaned_abstract = abstract.replace('\n', ' ').replace('- ', '')
+
+    return cleaned_abstract
+
+def summarize_text(hf_model_name, text):
+    """
+    Summarizes the given text using a Hugging Face model.
+    """
+    summarizer = pipeline("summarization", model=hf_model_name)
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+    return summary
+
+def text_to_speech(text):
+    """
+    Converts text to speech using a Hugging Face model.
+    """
+    models, cfg, task = load_model_ensemble_and_task_from_hf_hub(
+        "facebook/fastspeech2-en-ljspeech",
+        arg_overrides={"vocoder": "hifigan", "fp16": False}
+    )
+    model = models[0]
+    TTSHubInterface.update_cfg_with_data_cfg(cfg, task.data_cfg)
+    generator = task.build_generator([model], cfg)
+    sample = TTSHubInterface.get_model_input(task, text)
+    wav, rate = TTSHubInterface.get_prediction(task, model, generator, sample)
+    
+    return wav, rate
+
+def process_pdf(uploaded_file, hf_model_name):
+    """
+    Processes the uploaded PDF file to extract, summarize the abstract, and convert it to speech.
+    """
+    abstract = extract_and_clean_abstract(uploaded_file)
+    summary = summarize_text(hf_model_name, abstract)
+    wav, rate = text_to_speech(summary)
+    sf.write('/tmp/speech_output.wav', wav, rate)
+    return '/tmp/speech_output.wav'
+
+iface = gr.Interface(
+    fn=process_pdf,
+    inputs=[
+        gr.inputs.File(label="Upload PDF", type="pdf"),
+        gr.inputs.Textbox(label="Hugging Face Model Name for Summarization")
+    ],
+    outputs=gr.outputs.Audio(label="Audio Summary"),
+    title="PDF Abstract to Speech",
+    description="Extracts and summarizes the abstract from a PDF file and converts it to speech."
+)
+
+if __name__ == "__main__":
+    iface.launch()
+