Update app.py

app.py

@@ -1,26 +1,34 @@
-import gradio as gr
-from PIL import Image
-import pytesseract
+import os
 from gtts import gTTS
+from pdfminer.high_level import extract_text
+import gradio as gr
 import os
 
-# Función para convertir imagen a texto
-def image_to_text(imagen):
-    texto = pytesseract.image_to_string(Image.open(imagen))
-    return texto
 
-# Función para convertir texto a audio
-def text_to_audio(texto):
-    audio = gTTS(text=texto, lang='es', slow=False)
-    audio.save("audio.mp3")
-    return "audio.mp3"
+def pdf_to_text(file_obj):
+    text = extract_text(file_obj.name)
+    myobj = gTTS(text=text, lang='en', slow=False) 
+    myobj.save("test.wav") 
+    return 'test.wav'
+
+
+examples = [
+    [os.path.abspath("short-pdf.pdf")],
+    [os.path.abspath("long-pdf.pdf")]
+]
+
 
-# Función que combina las dos funciones anteriores
-def imagen_a_audio(imagen):
-    texto = image_to_text(imagen)
-    audio = text_to_audio(texto)
-    return audio
+iface = gr.Interface(fn = pdf_to_text,
+                     inputs = 'file',
+                     outputs = 'audio', 
+                     verbose = True,
+                     title = 'PDF to Audio Application',
+                     description = 'A simple application to convert PDF files in audio speech. Upload your own file, or click one of the examples to load them.',
+                     article = 
+                        '''<div>
+                            <p style="text-align: center"> All you need to do is to upload the pdf file and hit submit, then wait for compiling. After that click on Play/Pause for listing to the audio. The audio is saved in a wav format.</p>
+                        </div>''',
+                     examples=examples
+                    )
 
-# Crear la interfaz de usuario con Gradio
-iface = gr.Interface(fn=imagen_a_audio, inputs="Image", outputs="Audio")
 iface.launch()