import PyPDF2
from transformers import pipeline
import gradio as gr

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    reader = PyPDF2.PdfReader(pdf_file)
    text = ""
    for page in reader.pages:
        if page and page.extract_text():
            text += page.extract_text()
    return text

# Load text-to-speech pipeline from Hugging Face
tts = pipeline("text-to-speech", model="facebook/fastspeech2-en-ljspeech")

# Function to convert PDF to audio with no text limit
def pdf_to_audio(pdf_file):
    text = extract_text_from_pdf(pdf_file)
    if not text.strip():
        return "", "No text found in PDF"

    audio = tts(text)
    audio_path = "output_audio.wav"
    with open(audio_path, "wb") as f:
        f.write(audio["audio"])  # Hugging Face TTS returns audio data

    return audio_path, "Audio generated successfully"

# Gradio interface
interface = gr.Interface(
    fn=pdf_to_audio,
    inputs=gr.File(type="file"),
    outputs=[gr.Audio(type="filepath"), gr.Text()]
)

if __name__ == "__main__":
    interface.launch()