mobenta commited on
Commit
53e0ff0
·
verified ·
1 Parent(s): 8d66f7e

Upload 2 files

Browse files
Files changed (2) hide show
  1. app (1).py +45 -0
  2. requirements (6).txt +8 -0
app (1).py ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ import cohere
3
+ import gradio as gr
4
+ from pypdf import PdfReader
5
+ import os
6
+ from loguru import logger
7
+ import promptic
8
+
9
+ # Initialize Cohere client with your API key
10
+ cohere_client = cohere.Client(os.getenv("COHERE_API_KEY"))
11
+
12
+ # Function to extract text from PDF
13
+ def extract_text_from_pdf(pdf_file):
14
+ reader = PdfReader(pdf_file)
15
+ text = ""
16
+ for page in reader.pages:
17
+ text += page.extract_text()
18
+ return text
19
+
20
+ # Function to convert PDF text to audio via Cohere
21
+ def pdf_to_audio(pdf_file):
22
+ try:
23
+ text = extract_text_from_pdf(pdf_file)
24
+
25
+ # Generate response using Cohere
26
+ response = cohere_client.generate(
27
+ model='xlarge', # Change the model if necessary
28
+ prompt=text,
29
+ max_tokens=500 # Adjust based on your needs
30
+ )
31
+ generated_text = response.generations[0].text.strip()
32
+
33
+ # You could add audio generation code here or use text-to-speech libraries
34
+
35
+ return generated_text # Returning text for now
36
+ except Exception as e:
37
+ logger.error(f"Error during PDF to audio conversion: {e}")
38
+ return "An error occurred while processing the PDF."
39
+
40
+ # Gradio interface
41
+ def gradio_interface(pdf_file):
42
+ return pdf_to_audio(pdf_file)
43
+
44
+ # Launch the Gradio interface
45
+ gr.Interface(fn=gradio_interface, inputs="file", outputs="text", title="PDF to Audio using Cohere").launch()
requirements (6).txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+
2
+ gradio
3
+ pandas
4
+ pypdf
5
+ loguru
6
+ promptic
7
+ tenacity
8
+ cohere