Update app.py

app.py

@@ -2,32 +2,14 @@ import gradio as gr
 from PIL import Image, ImageDraw, ImageFont
 import scipy.io.wavfile as wavfile
 
-
-# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-# model_path = ("../Models/models--facebook--detr-resnet-50/snapshots"
-#               "/1d5f47bd3bdd2c4bbfa585418ffe6da5028b4c0b")
-#
-# tts_model_path = ("../Models/models--kakao-enterprise--vits-ljs/snapshots"
-#                   "/3bcb8321394f671bd948ebf0d086d694dda95464")
-
-
 narrator = pipeline("text-to-speech",
                     model="kakao-enterprise/vits-ljs")
 
 object_detector = pipeline("object-detection",
                 model="facebook/detr-resnet-50")
 
-# object_detector = pipeline("object-detection",
-#                 model=model_path)
-#
-# narrator = pipeline("text-to-speech",
-#                     model=tts_model_path)
-
-# [{'score': 0.9996405839920044, 'label': 'person', 'box': {'xmin': 435, 'ymin': 282, 'xmax': 636, 'ymax': 927}}, {'score': 0.9995879530906677, 'label': 'dog', 'box': {'xmin': 570, 'ymin': 694, 'xmax': 833, 'ymax': 946}}]
-
-# Define the function to generate audio from text
 def generate_audio(text):
     # Generate the narrated text
     narrated_text = narrator(text)
@@ -39,10 +21,6 @@ def generate_audio(text):
     # Return the path to the saved audio file
     return "output.wav"
 
-# Could you please write me a python code that will take list of detection object as an input and it will give the response that will include all the objects (labels) provided in the input. For example if the input is like this: [{'score': 0.9996405839920044, 'label': 'person', 'box': {'xmin': 435, 'ymin': 282, 'xmax': 636, 'ymax': 927}}, {'score': 0.9995879530906677, 'label': 'dog', 'box': {'xmin': 570, 'ymin': 694, 'xmax': 833, 'ymax': 946}}]
-# The output should be, This pictuture contains 1 person and 1 dog. If there are multiple objects, do not add 'and' between every objects but 'and' should be at the end only
-
-
 def read_objects(detection_objects):
     # Initialize counters for each object label
     object_counts = {}
@@ -136,6 +114,5 @@ def detect_object(image):
 demo = gr.Interface(fn=detect_object,
                     inputs=[gr.Image(label="Select Image",type="pil")],
                     outputs=[gr.Image(label="Processed Image", type="pil"), gr.Audio(label="Generated Audio")],
-                    title="@GenAILearniverse Project 7: Object Detector with Audio",
                     description="THIS APPLICATION WILL BE USED TO HIGHLIGHT OBJECTS AND GIVES AUDIO DESCRIPTION FOR THE PROVIDED INPUT IMAGE.")
 demo.launch()