this code is good but output not coming in huggingface

app.py

@@ -2,9 +2,11 @@ import cv2
 import mediapipe as mp
 import numpy as np
 import gradio as gr
+import tempfile
 
-# MediaPipe setup
+# Load model
 MODEL_PATH = "hand_landmarker.task"
+
 BaseOptions = mp.tasks.BaseOptions
 HandLandmarker = mp.tasks.vision.HandLandmarker
 HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
@@ -44,42 +46,61 @@ def get_finger_color(start_idx):
     else:
         return FINGER_COLORS['palm']
 
-# Load model only once
-options = HandLandmarkerOptions(
-    base_options=BaseOptions(model_asset_path=MODEL_PATH),
-    running_mode=VisionRunningMode.IMAGE,
-    num_hands=2,
-    min_hand_detection_confidence=0.5,
-    min_hand_presence_confidence=0.5,
-    min_tracking_confidence=0.5
+def process_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
+    out_path = tmp_out.name
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
+
+    options = HandLandmarkerOptions(
+        base_options=BaseOptions(model_asset_path=MODEL_PATH),
+        running_mode=VisionRunningMode.IMAGE,
+        num_hands=2,
+        min_hand_detection_confidence=0.5,
+        min_hand_presence_confidence=0.5,
+        min_tracking_confidence=0.5
+    )
+
+    with HandLandmarker.create_from_options(options) as landmarker:
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
+            results = landmarker.detect(mp_img)
+
+            if results.hand_landmarks:
+                for hand_landmarks in results.hand_landmarks:
+                    points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
+
+                    for start, end in HAND_CONNECTIONS:
+                        color = get_finger_color(start)
+                        cv2.line(frame, points[start], points[end], color, 2)
+
+                    for i, (x, y) in enumerate(points):
+                        cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
+
+            out.write(frame)
+
+    cap.release()
+    out.release()
+    return out_path
+
+# Gradio interface
+demo = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Upload Video or Use Webcam"),
+    outputs=gr.Video(label="Hand Landmark Annotated Video"),
+    title="Hand Detection ",
+    description="Upload a video or use webcam to detect hands."
 )
-landmarker = HandLandmarker.create_from_options(options)
-
-# Main processing function
-def detect_hand(frame):
-    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-    mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
-    results = landmarker.detect(mp_img)
-
-    h, w, _ = frame.shape
-    if results.hand_landmarks:
-        for hand_landmarks in results.hand_landmarks:
-            points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
-
-            for start, end in HAND_CONNECTIONS:
-                color = get_finger_color(start)
-                cv2.line(frame, points[start], points[end], color, 2)
-
-            for (x, y) in points:
-                cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
-
-    return frame
-
-# Gradio UI
-gr.Interface(
-    fn=detect_hand,
-    inputs=gr.Image(source="webcam", streaming=True, label="Webcam Input"),
-    outputs=gr.Image(label="Annotated Frame"),
-    title="Real-time Hand Detection with MediaPipe",
-    live=True
-).launch()
+
+demo.launch()