1.0.1

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import AutoModel, AutoProcessor
+import torch
+import cv2
+
+# Load the model and processor from Hugging Face Hub
+model_name = "OpenGVLab/InternVideo2_5_Chat_8B"  # Replace with the correct model name
+model = AutoModel.from_pretrained(model_name,trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(model_name,trust_remote_code=True)
+
+def predict(video_path):
+    # Load the video
+    video = cv2.VideoCapture(video_path)
+    frames = []
+    while True:
+        ret, frame = video.read()
+        if not ret:
+            break
+        frames.append(frame)
+    video.release()
+
+    # Preprocess the frames
+    inputs = processor(frames, return_tensors="pt")
+
+    # Perform inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # Process the outputs (replace this with your actual logic)
+    prediction = "Hello (Example Prediction)"
+    return prediction
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Video(label="Upload Video"),
+    outputs=gr.Textbox(label="Prediction"),
+    title="Indian Sign Language Recognition",
+    description="Upload a video to recognize Indian Sign Language gestures.",
+)
+
+# Launch the interface
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+torch
+torchvision
+opencv-python
+gradio