Update app.py

app.py

@@ -1,19 +1,5 @@
 
 
-import streamlit as st
-
-
-#from transformers import pipeline
-
-"""
-pipe = pipeline ('sentiment-analysis')
-text = st.text_area("some text")
-
-if text:
-    out = pipe(text)
-    st.json(out)
-
-"""
 import os
 HF_TOKEN = os.getenv('HF_TOKEN')
 
@@ -23,43 +9,49 @@ from huggingface_hub import HfFolder
 HfFolder.save_token(HF_TOKEN)
 
 
-prompt = st.text_area("some text")
-
-
-import torch
-import torchaudio
-from einops import rearrange
-from stable_audio_tools import get_pretrained_model
-from stable_audio_tools.inference.generation import generate_diffusion_cond
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-# Download model
-model, model_config = get_pretrained_model("stabilityai/stable-audio-open-1.0")
-sample_rate = model_config["sample_rate"]
-sample_size = model_config["sample_size"]
-
-model = model.to(device)
-
-# Set up text and timing conditioning
-conditioning = [{
-	"prompt": prompt
-}]
-
-# Generate stereo audio
-output = generate_diffusion_cond(
-	model,
-	conditioning=conditioning,
-	sample_size=sample_size,
-	device=device
-)
-
-# Rearrange audio batch to a single sequence
-output = rearrange(output, "b d n -> d (b n)")
+from transformers import pipeline, AutoTokenizer, AutoModel
+import streamlit as st
 
-# Peak normalize, clip, convert to int16, and save to file
-output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
-torchaudio.save("output.wav", output, sample_rate)
+# Set Hugging Face API Token if required
+"""
+os.environ["HF_HOME"] = "path_to_your_huggingface_cache_directory"
+os.environ["TRANSFORMERS_CACHE"] = "path_to_your_transformers_cache_directory"
+os.environ["HF_DATASETS_CACHE"] = "path_to_your_datasets_cache_directory"
+os.environ["HF_METRICS_CACHE"] = "path_to_your_metrics_cache_directory"
+os.environ["HF_MODULES_CACHE"] = "path_to_your_modules_cache_directory"
+os.environ["HF_TOKEN"] = "your_hugging_face_access_token"
+"""
 
+# Setup Streamlit interface for input
+st.title("Image to Text Model")
+
+# Using Pipeline
+st.header("Using Pipeline for Image Captioning")
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Assuming the pipeline handles image files directly
+    pipe = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+    try:
+        result = pipe(uploaded_file.getvalue())
+        st.write("Generated Caption:", result[0]['generated_text'])
+    except Exception as e:
+        st.error(f"Failed to generate caption: {str(e)}")
+
+# Load model directly for further analysis or different processing steps
+st.header("Load Model Directly")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+model = AutoModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+
+# Example of how you might use model and tokenizer directly
+# This section can be customized based on what you need to do with the model
+if st.button("Load Model Information"):
+    try:
+        st.text("Model and Tokenizer loaded successfully")
+        # Display some model details, for example:
+        st.text(f"Model Architecture: {model.__class__.__name__}")
+        st.text(f"Tokenizer Type: {tokenizer.__class__.__name__}")
+    except Exception as e:
+        st.error(f"Error loading model: {str(e)}")