Upload app.py

app.py

@@ -1,23 +1,3 @@
-import subprocess
-import sys
-
-# def install(package):
-#     subprocess.check_call([sys.executable, "-m", "pip", "install", package])
-
-# install("evaluate")
-# install("jiwer")
-# install("huggingface_hub")
-# install("gradio")
-# install("bitsandbytes")
-# install("git+https://github.com/huggingface/transformers.git")
-# install("git+https://github.com/huggingface/peft.git")
-# install("git+https://github.com/huggingface/accelerate.git")
-# install("einops")
-# install("safetensors")
-# install("torch")
-# install("xformers")
-# install("datasets")
-
 from transformers import AutoProcessor, AutoModelForCausalLM, BitsAndBytesConfig
 import torch
 from PIL import Image
@@ -130,6 +110,7 @@ from peft import (
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, AutoConfig
 from peft import LoraConfig, get_peft_model
 
+
 os.environ["CUDA_VISIBLE_DEVICES"] = "0"
 
 class Social_Media_Captioner:
@@ -207,7 +188,7 @@ class Social_Media_Captioner:
             self.model_loaded = False
 
 
-    def inference(self, input_text: str, use_cached=True, cache_generation=True) -> str | None:
+    def inference(self, input_text: str, use_cached=True, cache_generation=True):
         if not self.model_loaded:
             raise Exception("Model not loaded")
 
@@ -249,7 +230,7 @@ class Social_Media_Captioner:
             raise Exception("Enter a valid input text to generate a valid prompt")
 
         return f"""
-            Convert the given image description to social media worthy metaphoric caption
+            Convert the given image description to social media worthy caption
             Description: {input_text}
             Caption:
             """.strip()
@@ -304,14 +285,12 @@ caption_generator = Captions()
 import gradio as gr
 
 def setup(image):
-    # Assuming `caption_generator.generate_captions` is your function to generate captions.
-    # This is just a placeholder for your actual caption generation logic.
     return caption_generator.generate_captions(image = image)
 
 iface = gr.Interface(
     fn=setup,
-    inputs=gr.Image(type="pil", label="Upload Image"),  # Updated usage here
-    outputs="text"  # Simplified usage here
+    inputs=gr.inputs.Image(type="pil", label="Upload Image"),
+    outputs=gr.outputs.Textbox(label="Caption")
 )
 
-iface.launch()
+iface.launch()