Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -1,48 +1,48 @@
|
|
1 |
-
# Importing the requirements
|
2 |
-
# import warnings
|
3 |
-
|
4 |
-
# warnings.filterwarnings("ignore")
|
5 |
-
|
6 |
-
import gradio as gr
|
7 |
-
from src.model import describe_video
|
8 |
-
|
9 |
-
|
10 |
-
# Video and text inputs for the interface
|
11 |
-
video = gr.Video(
|
12 |
-
query = gr.Textbox(label="Query", placeholder="Type your query here")
|
13 |
-
|
14 |
-
# Output for the interface
|
15 |
-
response = gr.Textbox(label="Response", show_label=True, show_copy_button=True)
|
16 |
-
|
17 |
-
# Examples for the interface
|
18 |
-
examples = [
|
19 |
-
[
|
20 |
-
"./videos/sample_video_1.mp4",
|
21 |
-
"Here are some frames of a video. Describe this video in detail",
|
22 |
-
],
|
23 |
-
[
|
24 |
-
"./videos/sample_video_2.mp4",
|
25 |
-
"Which are the animals in this video, and how many are there?",
|
26 |
-
],
|
27 |
-
["./videos/sample_video_3.mp4", "What is happening in this video?"],
|
28 |
-
]
|
29 |
-
|
30 |
-
# Title, description, and article for the interface
|
31 |
-
title = "Video Understanding & Question Answering"
|
32 |
-
description = "This Gradio demo uses the MiniCPM-V-2_6 model for video understanding tasks. Upload a video and type a question to get a detailed description or specific information from the video."
|
33 |
-
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2407.03320' target='_blank'>InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output</a> | <a href='https://huggingface.co/internlm/internlm-xcomposer2d5-7b' target='_blank'>Model Page</a></p>"
|
34 |
-
|
35 |
-
|
36 |
-
# Launch the interface
|
37 |
-
interface = gr.Interface(
|
38 |
-
fn=describe_video,
|
39 |
-
inputs=[video, query],
|
40 |
-
outputs=response,
|
41 |
-
examples=examples,
|
42 |
-
title=title,
|
43 |
-
description=description,
|
44 |
-
article=article,
|
45 |
-
theme="Soft",
|
46 |
-
allow_flagging="never",
|
47 |
-
)
|
48 |
-
interface.launch(debug=False)
|
|
|
1 |
+
# Importing the requirements
|
2 |
+
# import warnings
|
3 |
+
|
4 |
+
# warnings.filterwarnings("ignore")
|
5 |
+
|
6 |
+
import gradio as gr
|
7 |
+
from src.model import describe_video
|
8 |
+
|
9 |
+
|
10 |
+
# Video and text inputs for the interface
|
11 |
+
video = gr.Video(label="Video")
|
12 |
+
query = gr.Textbox(label="Query", placeholder="Type your query here")
|
13 |
+
|
14 |
+
# Output for the interface
|
15 |
+
response = gr.Textbox(label="Response", show_label=True, show_copy_button=True)
|
16 |
+
|
17 |
+
# Examples for the interface
|
18 |
+
examples = [
|
19 |
+
[
|
20 |
+
"./videos/sample_video_1.mp4",
|
21 |
+
"Here are some frames of a video. Describe this video in detail",
|
22 |
+
],
|
23 |
+
[
|
24 |
+
"./videos/sample_video_2.mp4",
|
25 |
+
"Which are the animals in this video, and how many are there?",
|
26 |
+
],
|
27 |
+
["./videos/sample_video_3.mp4", "What is happening in this video?"],
|
28 |
+
]
|
29 |
+
|
30 |
+
# Title, description, and article for the interface
|
31 |
+
title = "Video Understanding & Question Answering"
|
32 |
+
description = "This Gradio demo uses the MiniCPM-V-2_6 model for video understanding tasks. Upload a video and type a question to get a detailed description or specific information from the video."
|
33 |
+
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2407.03320' target='_blank'>InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output</a> | <a href='https://huggingface.co/internlm/internlm-xcomposer2d5-7b' target='_blank'>Model Page</a></p>"
|
34 |
+
|
35 |
+
|
36 |
+
# Launch the interface
|
37 |
+
interface = gr.Interface(
|
38 |
+
fn=describe_video,
|
39 |
+
inputs=[video, query],
|
40 |
+
outputs=response,
|
41 |
+
examples=examples,
|
42 |
+
title=title,
|
43 |
+
description=description,
|
44 |
+
article=article,
|
45 |
+
theme="Soft",
|
46 |
+
allow_flagging="never",
|
47 |
+
)
|
48 |
+
interface.launch(debug=False)
|