Update app.py

app.py

@@ -1,32 +1,55 @@
 import os
-from PyPDF2 import PdfReader
+from PyPDF2 import PdfReader, PdfReadError
 from gtts import gTTS
+from pydub import AudioSegment
 import gradio as gr
 
 def pdf_to_text(pdf_file):
-    reader = PdfReader(pdf_file)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text()
-    return text
+    try:
+        reader = PdfReader(pdf_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        return text
+    except PdfReadError:
+        return None
 
-def text_to_speech(text, lang='en'):
+def text_to_speech(text, lang='en', file_format='mp3'):
     tts = gTTS(text=text, lang=lang)
-    output_path = "output.mp3"
-    tts.save(output_path)
+    output_path = f"output.{file_format}"
+    tts.save("temp.mp3")
+    
+    if file_format == 'mp3':
+        os.rename("temp.mp3", output_path)
+    elif file_format == 'wav':
+        sound = AudioSegment.from_mp3("temp.mp3")
+        sound.export(output_path, format="wav")
+        os.remove("temp.mp3")
+    
     return output_path
 
-def convert_pdf_to_speech(pdf_file):
+def convert_pdf_to_speech(pdf_file, lang='en', file_format='mp3'):
     text = pdf_to_text(pdf_file)
-    audio_file = text_to_speech(text)
-    return audio_file
+    if text:
+        audio_file = text_to_speech(text, lang=lang, file_format=file_format)
+        return audio_file
+    else:
+        return "Error: Could not read the PDF file. Please upload a valid PDF."
 
 # Gradio arayüzü
-def interface(pdf_file):
-    audio_file = convert_pdf_to_speech(pdf_file.name)
+def interface(pdf_file, lang, file_format):
+    audio_file = convert_pdf_to_speech(pdf_file.name, lang=lang, file_format=file_format)
     return audio_file
 
-iface = gr.Interface(fn=interface, inputs="file", outputs="file", 
-                     title="Pdf Seslendirme",
-                     description="PDF dosyasını yükleyin ve onu MP3 formatındaki sese dönüştürün.")
-iface.launch()
+iface = gr.Interface(
+    fn=interface, 
+    inputs=[
+        gr.inputs.File(label="Upload PDF"),
+        gr.inputs.Dropdown(choices=["en", "es", "fr", "de", "it", "tr", "zh", "jp"], label="Select Language"),
+        gr.inputs.Radio(choices=["mp3", "wav"], label="Select Output Format")
+    ], 
+    outputs="file", 
+    title="PDF to Speech Converter",
+    description="Upload a PDF file, select the language, and choose the output format (MP3 or WAV)."
+)
+iface.launch(share=True)