Instructions to use Moustafa3092/livekit-turn-detector-arabic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Moustafa3092/livekit-turn-detector-arabic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Moustafa3092/livekit-turn-detector-arabic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Moustafa3092/livekit-turn-detector-arabic")
model = AutoModelForCausalLM.from_pretrained("Moustafa3092/livekit-turn-detector-arabic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Moustafa3092/livekit-turn-detector-arabic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Moustafa3092/livekit-turn-detector-arabic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Moustafa3092/livekit-turn-detector-arabic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Moustafa3092/livekit-turn-detector-arabic

SGLang

How to use Moustafa3092/livekit-turn-detector-arabic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Moustafa3092/livekit-turn-detector-arabic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Moustafa3092/livekit-turn-detector-arabic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Moustafa3092/livekit-turn-detector-arabic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Moustafa3092/livekit-turn-detector-arabic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Moustafa3092/livekit-turn-detector-arabic with Docker Model Runner:
```
docker model run hf.co/Moustafa3092/livekit-turn-detector-arabic
```

LiveKit Turn Detector - Arabic

Fine-tuned Arabic End-of-Utterance (EOU) detection model for LiveKit voice agents.

Model Details

Base Model: livekit/turn-detector (Qwen2-0.5B)
Fine-tuning Method: LoRA (rank=32, alpha=64)
Dataset: 57,475 Arabic EOU samples
Languages: Arabic (ar, ar-SA, ar-EG, Gulf dialects)
Training: 3 epochs on T4 GPU (~20-30 minutes)
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Use Cases

Real-time Arabic voice agents with LiveKit
Turn-taking detection in Arabic conversations
End-of-utterance detection for Gulf Arabic dialects
Multilingual voice assistants with Arabic support

Usage

Basic Usage with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model
model = AutoModelForCausalLM.from_pretrained("Moustafa3092/livekit-turn-detector-arabic")
tokenizer = AutoTokenizer.from_pretrained("Moustafa3092/livekit-turn-detector-arabic", trust_remote_code=True)

# Predict EOU
def predict_eou(text: str) -> float:
    formatted = f"<|im_start|>user\n{text}"
    inputs = tokenizer(formatted, return_tensors="pt", add_special_tokens=False)

    with torch.no_grad():
        logits = model(**inputs).logits[0, -1, :]
        probs = torch.softmax(logits, dim=-1)
        eou_prob = probs[tokenizer.convert_tokens_to_ids("<|im_end|>")]

    return eou_prob.item()

# Test
print(predict_eou("شكرا جزيلا"))  # Should be high (complete)
print(predict_eou("اممممم"))      # Should be low (incomplete)

With LiveKit Voice Agents

Export to ONNX:

# Convert model to ONNX format for production
# See deployment documentation

Use in LiveKit Agent:

from livekit.agents import WorkerOptions, cli
from livekit.plugins import turn_detector

# Configure with your fine-tuned model
turn_detector.configure(model_path="path/to/model.onnx")

Training Data

Dataset Composition (57,475 samples)

Complete Utterances (EOU): 20,194 (35.1%)

CSV data: 19,432 samples
Edge case closures: 762 samples
Examples: "شكرا" (thank you), "تمام" (perfect), "مع السلامة" (goodbye)

Incomplete Utterances (non-EOU): 37,281 (64.9%)

Generated variants: 36,610 samples
Edge case hesitations: 671 samples
Examples: "اممممم" (ummm...), "يعني" (you know...), "بس" (but...)

Edge Cases (1,433 samples)

Hesitations (Non-EOU) - Speaker thinking, will continue:

اممممم, يعني, خلاص بس, طيب و

Closures (EOU) - Complete short responses:

شكرا, تمام, نعم, لا, مع السلامة

Performance

Accuracy: >90% on Arabic edge cases
Training Time: ~20-30 minutes (T4 GPU)
Memory: ~6 GB VRAM during training
Inference: Real-time compatible
Model Size: 494 MB (full model)

Model Architecture

Architecture: Qwen2-0.5B (Causal LM)
Parameters: ~500M total
Fine-tuned: LoRA adapters merged
Context Length: Supports conversation context
Output: EOU probability via <|im_end|> token

Limitations

Optimized for Modern Standard Arabic and Gulf dialects
May need additional fine-tuning for other Arabic dialects
Requires sufficient context for accurate predictions
Best performance on conversational Arabic

Citation

If you use this model, please cite:

@misc{livekit-turn-detector-arabic,
  author = {Moustafa3092},
  title = {LiveKit Turn Detector - Arabic},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/Moustafa3092/livekit-turn-detector-arabic}
}

License

Apache 2.0

Acknowledgements

Based on LiveKit Turn Detector
Built with Transformers and PEFT
Fine-tuned for Arabic language support

Developed by: Moustafa3092 Model Type: Turn Detection / End-of-Utterance Language: Arabic (ar) Base Model: livekit/turn-detector (v0.4.1-intl)

Downloads last month: 300

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for Moustafa3092/livekit-turn-detector-arabic

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

livekit/turn-detector

Finetuned

(2)

this model