Hugging Face's logo

Spaces:
links-ads
/
multimodal_emotion_recognition
Running

App Files Community
JuanJoseMV commited on
Commit
9995d17
·
1 Parent(s): 18e3ba4

add project description and texts

Browse files
Files changed (6) hide show
  1. .gitignore +19 -0
  2. app.py +29 -0
  3. project_info/description.txt +0 -0
  4. project_info/project_description.html +74 -0
  5. requirements.txt +2 -0
  6. src/load_html.py +7 -0
.gitignore CHANGED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Python
2
+ __pycache__/
3
+ *.py[cod]
4
+ *.pyo
5
+ *.pyd
6
+ *.env
7
+ *.venv
8
+ *.egg
9
+ *.egg-info/
10
+ dist/
11
+ build/
12
+ *.log
13
+
14
+ # Virtual Environment
15
+ .venv/
16
+
17
+ # VSCode
18
+ .vscode/
19
+ *.code-workspace
app.py CHANGED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ import plotly.graph_objects as go
3
+ from src.load_html import get_description_html
4
+
5
+ def process_audio(audio_file):
6
+ ...
7
+
8
+
9
+ # Gradio interface
10
+ def create_demo():
11
+ with gr.Blocks() as demo:
12
+ gr.HTML(get_description_html)
13
+
14
+ audio_input = gr.Audio(label="Upload Audio", type="filepath")
15
+ submit_button = gr.Button("Generate Graph")
16
+
17
+ graph_output = gr.Plot(label="Generated Graph")
18
+
19
+ submit_button.click(
20
+ fn=process_audio,
21
+ inputs=audio_input,
22
+ outputs=graph_output
23
+ )
24
+
25
+ return demo
26
+
27
+ if __name__ == "__main__":
28
+ demo = create_demo()
29
+ demo.launch(show_api=False)
project_info/description.txt DELETED
File without changes
project_info/project_description.html ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <head>
2
+ <meta charset="UTF-8">
3
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
4
+ <title>System for the Automatic Recognition of Affective Responses</title>
5
+ <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Montserrat">
6
+ <style>
7
+ body {
8
+ margin: 0;
9
+ padding: 0;
10
+ font-family: 'Montserrat';
11
+ }
12
+ .container {
13
+ position: relative;
14
+ width: 100;
15
+ margin: 0;
16
+ padding: 0px 20px;
17
+ word-wrap: break-word;
18
+ }
19
+ .title {
20
+ font-size: 36px;
21
+ margin-left: 100px;
22
+ }
23
+ .subtitle {
24
+ font-size: 24px;
25
+ color: #666;
26
+ line-height: 1.4;
27
+ margin-left: 100px;
28
+ }
29
+ .item {
30
+ font-weight: bold;
31
+ font-size: 32px;
32
+ padding-bottom: 10px;
33
+ }
34
+ .item-border {
35
+ border-bottom: 2px solid #edab3c;
36
+ display: inline-block;
37
+ padding-bottom: 10px;
38
+ }
39
+ .item-subtitle {
40
+ font-size: 20px;
41
+ font-weight: normal;
42
+ margin-left: 40px;
43
+ }
44
+ .item-border-locked {
45
+ border-bottom: 2px solid #f3f4f6;
46
+ display: inline-block;
47
+ padding-bottom: 10px;
48
+ }
49
+ </style>
50
+ </head>
51
+ <body>
52
+ <div class="container" style='height: auto; min-height: 160px; width: 100;'>
53
+ <div class="title">🌟 System for the Automatic Recognition of Affective Responses 🌟</div>
54
+ <div class="subtitle"> Affective Computing and Emotion Recognition </div>
55
+ </div>
56
+ <div class="item">
57
+ <div class="item-border">❓What is it?</div>
58
+ <div class="item-subtitle">
59
+ The System for the Automatic Recognition of Affective Responses is a project that aims to develop a system capable of recognizing and interpreting human emotions through various modalities, such as speech, facial expressions, and physiological signals. The goal is to create a comprehensive framework that can analyze and understand emotional responses in real-time, enabling applications in fields like human-computer interaction, mental health monitoring, and affective computing.
60
+ </div>
61
+ </div>
62
+ <div class="item">
63
+ <div class="item-border">🌟 Why is it important?</div>
64
+ <div class="item-subtitle">
65
+ Understanding human emotions is crucial for improving communication and interaction between humans and machines. By recognizing and interpreting emotional responses, we can enhance user experiences, develop more empathetic AI systems, and contribute to advancements in mental health care. This project aims to bridge the gap between technology and human emotions, paving the way for more intuitive and responsive systems.
66
+ </div>
67
+ </div>
68
+ <div class="item">
69
+ <div class="item-border">⚙️ How does it work?</div>
70
+ <div class="item-subtitle">
71
+ The system utilizes advanced machine learning algorithms and deep learning techniques to analyze multimodal data, including audio, visual, and physiological signals. By training on large datasets of annotated emotional responses, the system learns to recognize patterns and features associated with different emotions. The framework is designed to be adaptable and scalable, allowing for integration with various applications and platforms.
72
+ </div>
73
+ </div>
74
+ </body>
requirements.txt CHANGED
@@ -0,0 +1,2 @@
 
 
 
1
+ gradio==5.24.0
2
+ plotly==6.0.1
src/load_html.py ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ from pathlib import Path
2
+
3
+
4
+ HTML_DIR = Path("project_info")
5
+
6
+ def get_description_html():
7
+ return (HTML_DIR / "project_description.html").read_text(encoding="utf-8")