---
license: apache-2.0
base_model: google/efficientnet-b0
tags:
- image-classification
- sign-language
- asl
- efficientnet
- transformers
- vision
datasets:
- Marxulia/asl_sign_languages_alphabets_v03
metrics:
- accuracy
model-index:
- name: asl-sign-language-efficientnet-b0
  results:
  - task:
      type: image-classification
      name: Image Classification
    dataset:
      name: ASL Sign Languages Alphabets v03
      type: Marxulia/asl_sign_languages_alphabets_v03
    metrics:
    - type: accuracy
      value: 0.9902
      name: Accuracy
pipeline_tag: image-classification
---

# 🤟 ASL Sign Language Recognition — EfficientNet-B0

A fine-tuned **EfficientNet-B0** model for recognizing American Sign Language (ASL) alphabet letters from images. Achieves **99.02% accuracy** on the evaluation set.

## Model Details

| Property | Value |
|----------|-------|
| **Base Model** | [google/efficientnet-b0](https://huggingface.co/google/efficientnet-b0) (ImageNet pretrained) |
| **Parameters** | 4,040,854 (~15.6MB) |
| **Input Size** | 224×224 RGB images |
| **Classes** | 26 (A-Z ASL alphabet letters) |
| **Inference Speed** | <10ms/frame on GPU, ~30ms on CPU |

## Training

| Hyperparameter | Value |
|----------------|-------|
| Learning Rate | 2e-4 |
| Batch Size | 16 |
| Epochs | 5 |
| Optimizer | AdamW |
| LR Scheduler | Cosine |
| Weight Decay | 1e-4 |
| Warmup Ratio | 5% |

### Training Results

| Epoch | Eval Accuracy | Eval Loss |
|-------|---------------|-----------|
| 1 | 89.45% | 0.405 |
| 2 | 97.67% | 0.096 |
| 3 | 98.28% | 0.056 |
| 4 | 98.71% | 0.047 |
| 5 | **99.02%** | 0.036 |

### Data Augmentation
- RandomResizedCrop (scale 0.8-1.0)
- RandomHorizontalFlip (p=0.3)
- RandomRotation (±15°)
- ColorJitter (brightness=0.3, contrast=0.3, saturation=0.2, hue=0.1)

## Usage

```python
from transformers import pipeline

classifier = pipeline("image-classification", model="abdollahhh/asl-sign-language-efficientnet-b0")
result = classifier("path/to/hand_sign.jpg")
print(result)
# [{'label': 'A', 'score': 0.98}, ...]
```

### Manual inference

```python
from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image
import torch

processor = AutoImageProcessor.from_pretrained("abdollahhh/asl-sign-language-efficientnet-b0")
model = AutoModelForImageClassification.from_pretrained("abdollahhh/asl-sign-language-efficientnet-b0")
model.eval()

image = Image.open("hand_sign.jpg")
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
    logits = model(**inputs).logits

predicted_class = logits.argmax(-1).item()
label = model.config.id2label[str(predicted_class)]
print(f"Predicted: {label}")
```

## Live Demo

Try the real-time webcam demo: [ASL Sign Language Recognition Space](https://huggingface.co/spaces/abdollahhh/asl-sign-language-recognition)

## Dataset

Trained on [Marxulia/asl_sign_languages_alphabets_v03](https://huggingface.co/datasets/Marxulia/asl_sign_languages_alphabets_v03):
- 10,873 images total (9,242 train / 1,631 eval)
- 26 classes: A through Z
- Stratified 85/15 train/eval split

## Limitations

- Trained on controlled studio images — may have reduced accuracy with varied backgrounds/lighting
- Only recognizes static letter signs (A-Z), not dynamic gestures (J, Z involve motion)
- Works best with a clean hand against a neutral background