Dan Mo commited on
Commit
ceedb93
Β·
1 Parent(s): b406b78

Update README.md to enhance description and features of the Feelings to Emoji application

Browse files
Files changed (1) hide show
  1. README.md +41 -3
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  title: Feelings To Emoji
3
- emoji: 🌍
4
  colorFrom: red
5
  colorTo: pink
6
  sdk: gradio
@@ -8,7 +8,45 @@ sdk_version: 5.25.0
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
- short_description: Converts text, speech, image or video to emoji.
12
  ---
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: Feelings To Emoji
3
+ emoji: 🎭
4
  colorFrom: red
5
  colorTo: pink
6
  sdk: gradio
 
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ short_description: Convert your emotions into emoji mashups with embedding models!
12
  ---
13
 
14
+ # Feelings to Emoji
15
+
16
+ This application uses sentence embeddings to match emotional text expressions with appropriate emojis and create unique emoji mashups.
17
+
18
+ ## 🌟 Features
19
+
20
+ - **Emotion Recognition**: Convert your emotional expressions into matching emojis
21
+ - **Emoji Mashups**: Generate creative combinations of emotion and event emojis
22
+ - **Multiple Embedding Models**: Choose from different embedding models to see how they interpret your emotions
23
+ - **Cached Embeddings**: Pre-computed embeddings for faster response times
24
+ - **Comprehensive Examples**: Built-in examples based on Plutchik's Wheel of Emotions
25
+
26
+ ## 🧠 Embedding Models
27
+
28
+ Three different sentence embedding models are available:
29
+
30
+ - **MPNet** (110M) - Balanced, great general-purpose model
31
+ - **GTE** (335M) - Context-rich, good for emotion & nuance
32
+ - **BGE** (350M) - Tuned for ranking & high-precision similarity
33
+
34
+ ## πŸ”„ How It Works
35
+
36
+ 1. Enter a sentence describing your feelings or emotions
37
+ 2. The system uses sentence embeddings to match your text with the most similar emotion emoji
38
+ 3. It also finds an event/object emoji that matches your text
39
+ 4. The two emojis are combined into a unique "emoji kitchen" mashup
40
+
41
+ ## πŸš€ Getting Started
42
+
43
+ To run this application locally:
44
+
45
+ 1. Clone this repository
46
+ 2. Install requirements: `pip install -r requirements.txt`
47
+ 3. Generate embeddings (optional): `python generate_embeddings.py`
48
+ 4. Run the app: `python app.py`
49
+
50
+ ## πŸ“š References
51
+
52
+ For more details about the implementation and API reference, see [REFERENCE.md](REFERENCE.md).