emojitrans
A fine-tuned multilingual emoji prediction model based on microsoft/Multilingual-MiniLM-L12-H384.
Given a text input, the model predicts the top-K most relevant emojis (32-class classification).
- Base model: Multilingual-MiniLM-L12-H384 (12-layer Transformer, hidden size 384)
- Training data: vincentclaes/emoji-predictor — 14,420 tweets
- Val Top-5 accuracy: 53%
- Runtime: ONNX (quantized), runs in-browser via onnxruntime-web
Files
| File | Description |
|---|---|
model_q8.onnx |
INT8 quantized ONNX model (~120 MB) |
tokenizer.json |
Tokenizer vocab & rules |
tokenizer_config.json |
Tokenizer config |
config.json |
Model architecture config |
id2label.json |
Label index → emoji character mapping |
- Downloads last month
- 4