videosdk-live/Namo-Turn-Detector-v1-Vietnamese

pip install onnxruntime transformers huggingface_hub

import numpy as np
import onnxruntime as ort
from transformers import AutoTokenizer
from huggingface_hub import hf_hub_download

class TurnDetector:
    def __init__(self, repo_id="videosdk-live/Namo-Turn-Detector-v1-Vietnamese"):
        """
        Initializes the detector by downloading the model and tokenizer
        from the Hugging Face Hub.
        """
        print(f"Loading model from repo: {repo_id}")
        
        # Download the model and tokenizer from the Hub
        # Authentication is handled automatically if you are logged in
        model_path = hf_hub_download(repo_id=repo_id, filename="model_quant.onnx")
        self.tokenizer = AutoTokenizer.from_pretrained(repo_id)
        
        # Set up the ONNX Runtime inference session
        self.session = ort.InferenceSession(model_path)
        self.max_length = 512
        print("✅ Model and tokenizer loaded successfully.")

    def predict(self, text: str) -> tuple:
        """
        Predicts if a given text utterance is the end of a turn.
        Returns (predicted_label, confidence) where:
        - predicted_label: 0 for "Not End of Turn", 1 for "End of Turn"
        - confidence: confidence score between 0 and 1
        """
        # Tokenize the input text
        inputs = self.tokenizer(
            text,
            truncation=True,
            max_length=self.max_length,
            return_tensors="np"
        )
        
        # Prepare the feed dictionary for the ONNX model
        feed_dict = {
            "input_ids": inputs["input_ids"],
            "attention_mask": inputs["attention_mask"]
        }
        
        # Run inference
        outputs = self.session.run(None, feed_dict)
        logits = outputs[0]

        probabilities = self._softmax(logits[0])
        predicted_label = np.argmax(probabilities)
        confidence = float(np.max(probabilities))

        return predicted_label, confidence

    def _softmax(self, x, axis=None):
        if axis is None:
            axis = -1
        exp_x = np.exp(x - np.max(x, axis=axis, keepdims=True))
        return exp_x / np.sum(exp_x, axis=axis, keepdims=True)

# --- Example Usage ---
if __name__ == "__main__":
    detector = TurnDetector()
    
    sentences = [
        "Vậy Relative Layout trong Android là gì?",      # Expected: End of Turn
        "Các loại rau ăn kèm rửa thật sạch để.", # Expected: Not End of Turn
    ]
    
    for sentence in sentences:
        predicted_label, confidence = detector.predict(sentence)
        result = "End of Turn" if predicted_label == 1 else "Not End of Turn"
        print(f"'{sentence}' -> {result} (confidence: {confidence:.3f})")
        print("-" * 50)

from videosdk_agents import NamoTurnDetectorV1, pre_download_namo_turn_v1_model

#download model
pre_download_namo_turn_v1_model(language="vi")

# Initialize Vietnamese turn detector for VideoSDK Agents
turn_detector = NamoTurnDetectorV1(language="vi")

@model{namo_turn_detector_vi_2025,
  title={Namo Turn Detector v1: Vietnamese},
  author={VideoSDK Team},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/videosdk-live/Namo-Turn-Detector-v1-Vietnamese},
  note={ONNX-optimized DistilBERT for turn detection in Vietnamese}
}