from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model_name = "hamza-amin/urdu-spam-classifier"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
def predict(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    outputs = model(**inputs)
    probs = torch.softmax(outputs.logits, dim=1)
    return probs.tolist()
print(predict("یہ ایک ایمرجنسی ہے فوراً مدد کریں"))
print(predict("ہیلو بس مذاق کر رہا تھا"))

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1146	1.0	169	0.1139	0.9834	0.9826	0.9860	0.9792
0.0902	2.0	338	0.0954	0.9834	0.9825	0.9929	0.9722
0.0085	3.0	507	0.0972	0.9867	0.9859	1.0	0.9722

Use Cases

Emergency call filtering
Spam detection in voice agents
Urdu NLP classification tasks

Limitations

Trained on synthetic data
May struggle with:
- slang / mixed Urdu-English
- very short inputs
- noisy speech-to-text output

Future Work

Add urgency classification (multi-class)
Train on real call data
Optimize for real-time inference (ONNX / quantization)

License

MIT