initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: MutimodalVisionAssistant
+emoji: 🏢
+colorFrom: yellow
+colorTo: red
+sdk: gradio
+sdk_version: 5.25.1
+app_file: app.py
+pinned: false
+license: mit
+short_description: Multimodal AI for Visual Impairment Support
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,35 @@
+# This is a simple Gradio app that handles image upload, webcam capture, and voice recording.
+import gradio as gr
+import numpy as np
+
+# Define a function to handle image upload and webcam capture.
+def handle_image(image):
+    return "Image received!", image  # Return a confirmation message and the image itself
+
+# Define a function to handle voice recording.
+def handle_voice(audio):
+    return "Voice recording received!", audio  # Return a confirmation message and the audio itself
+
+# Create a Gradio interface without the name and output boxes.
+with gr.Blocks() as demo:
+    # Add an image upload button
+    image_upload = gr.Image(label="Upload an Image", sources="upload")
+    # Add a webcam capture button
+    image_webcam = gr.Image(label="Take a Picture", sources="webcam")
+    # Add a button to record voice using the microphone
+    voice_record = gr.Audio(label="Record Voice", sources="microphone")
+    
+    # Add a column on the right to display the uploaded/captured image
+    with gr.Column():
+        image_display = gr.Image(label="Uploaded/Captured Image", interactive=False)
+        audio_display = gr.Audio(label="Recorded Voice", interactive=False)  # Add an audio display component
+
+    # Connect the image upload button to the handle_image function
+    image_upload.change(fn=handle_image, inputs=image_upload, outputs=[gr.Textbox(), image_display])
+    # Connect the webcam capture button to the handle_image function
+    image_webcam.change(fn=handle_image, inputs=image_webcam, outputs=[gr.Textbox(), image_display])
+    # Connect the voice recording button to the handle_voice function
+    voice_record.change(fn=handle_voice, inputs=voice_record, outputs=[gr.Textbox(), audio_display])
+
+if __name__ == "__main__":
+    demo.launch(show_error=True)

requirements.txt

@@ -0,0 +1 @@
+numpy