Initial Commit for Namo Turn Detector v1 (#1)

- Initial Commit for Namo Turn Detector v1 (b6eca82d36992e6045865c3dc2a2b43b7c58f334)

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+confusion_matrices.png filter=lfs diff=lfs merge=lfs -text
+performance_analysis.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,226 @@
+---
+language: ja
+license: apache-2.0
+library_name: onnxruntime
+pipeline_tag: text-classification
+tags:
+- turn-detection
+- end-of-utterance
+- distilbert
+- onnx
+- quantized
+- conversational-ai
+- voice-assistant
+- real-time
+base_model: distilbert-base-multilingual-cased
+datasets:
+- videosdk-live/Namo-Turn-Detector-v1-Train
+model-index:
+- name: Namo Turn Detector v1 - Japanese
+  results:
+  - task:
+      type: text-classification
+      name: Turn Detection
+    dataset:
+      name: Namo Turn Detector v1 Test - Japanese
+      type: videosdk-live/Namo-Turn-Detector-v1-Test
+      split: train
+    metrics:
+    - type: accuracy
+      value: 0.935252
+      name: Accuracy
+    - type: f1
+      value: 0.938776
+      name: F1 Score
+    - type: precision
+      value: 0.896104
+      name: Precision
+    - type: recall
+      value: 0.985714
+      name: Recall
+
+---
+
+# 🎯 Namo Turn Detector v1 - Japanese
+
+<div align="center">
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![ONNX](https://img.shields.io/badge/ONNX-Optimized-brightgreen)](https://onnx.ai/)
+[![Model Size](https://img.shields.io/badge/Model%20Size-~136M-orange)](https://huggingface.co/videosdk-live/Namo-Turn-Detector-v1-Japanese)
+[![Inference Speed](https://img.shields.io/badge/Inference-<14ms-red)]()
+
+**🚀 Namo Turn Detection Model for Japanese**
+
+</div>
+
+---
+
+## 📋 Overview
+
+The **Namo Turn Detector** is a specialized AI model designed to solve one of the most challenging problems in conversational AI: **knowing when a user has finished speaking**. 
+
+This Japanese-specialist model uses advanced natural language understanding to distinguish between:
+- ✅ **Complete utterances** (user is done speaking)
+- 🔄 **Incomplete utterances** (user will continue speaking)
+
+Built on DistilBERT architecture and optimized with quantized ONNX format, it delivers enterprise-grade performance with minimal latency.
+
+## 🔑 Key Features
+
+- **Turn Detection Specialist**: Detects end-of-turn vs. continuation in Japanese speech transcripts.  
+- **Low Latency**: Optimized with **quantized ONNX** for <14ms inference.  
+- **Robust Performance**: 93.5% accuracy on diverse Japanese utterances.  
+- **Easy Integration**: Compatible with Python, ONNX Runtime, and VideoSDK Agents SDK.  
+- **Enterprise Ready**: Supports real-time conversational AI and voice assistants.  
+
+## 📊 Performance Metrics
+<div>
+
+| Metric | Score |
+|--------|-------|
+| **🎯 Accuracy** | **93.52%** | 
+| **📈 F1-Score** | **93.87%** |
+| **🎪 Precision** | **89.61%** |
+| **🎭 Recall** | **98.57%** |
+| **⚡ Latency** | **<14ms** |
+| **💾 Model Size** | **~135MB** |
+
+</div>
+<img src="./confusion_matrices.png" alt="Alt text" width="600" height="400"/>
+
+> 📊 *Evaluated on 800+ Japanese utterances from diverse conversational contexts*
+
+## ⚡️ Speed Analysis
+
+<img src="./performance_analysis.png" alt="Alt text" width="600" height="400"/>
+
+## 🔧 Train & Test Scripts
+
+<div align="center">
+
+[![Train Script](https://img.shields.io/badge/Colab-Train%20Script-brightgreen?logo=google-colab)](https://colab.research.google.com/drive/1DqSUYfcya0r2iAEZB9fS4mfrennubduV) [![Test Script](https://img.shields.io/badge/Colab-Test%20Script-blue?logo=google-colab)](https://colab.research.google.com/drive/19ZOlNoHS2WLX2V4r5r492tsCUnYLXnQR)
+
+</div>
+
+## 🛠️ Installation
+
+To use this model, you will need to install the following libraries.
+
+```bash
+pip install onnxruntime transformers huggingface_hub
+```
+
+## 🚀 Quick Start
+
+You can run inference directly from Hugging Face repository.
+
+```python
+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-Japanese"):
+        """
+        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) -> str:
+        """
+        Predicts if a given text utterance is the end of a turn.
+        Returns "End of Turn" or "Not End of Turn".
+        """
+        # 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
+        
+        # Get the predicted class (0 or 1)
+        prediction_index = np.argmax(logits, axis=1)
+        
+        return "End of Turn" if prediction_index == 1 else "Not End of Turn"
+
+# --- Example Usage ---
+if __name__ == "__main__":
+    detector = TurnDetector()
+    
+    sentences = [
+        "1382年に聖パウロ修道会のために建てられた僧院です。",      # Expected: End of Turn
+        "1913年マニラで第1回東洋オリンピックが開会だから", # Expected: Not End of Turn
+
+    ]
+    
+    for sentence in sentences:
+        result = detector.predict(sentence)
+        print(f"'{sentence}' -> {result}")
+
+```
+
+
+## 🤖 VideoSDK Agents Integration
+
+Integrate this turn detector directly with VideoSDK Agents for production-ready conversational AI applications.
+
+```python
+from videosdk_agents import NamoTurnDetectorV1, pre_download_namo_turn_v1_model
+
+#download model
+pre_download_namo_turn_v1_model(language="ja")
+
+# Initialize Japanese turn detector for VideoSDK Agents
+turn_detector = NamoTurnDetectorV1(language="ja")
+```
+
+> 📚 [**Complete Integration Guide**](https://docs.videosdk.live/ai_agents/plugins/namo-turn-detector) - Learn how to use `NamoTurnDetectorV1` with VideoSDK Agents
+
+## 📖 Citation
+
+```bibtex
+@model{namo_turn_detector_ja_2025,
+  title={Namo Turn Detector v1: Japanese},
+  author={VideoSDK Team},
+  year={2025},
+  publisher={Hugging Face},
+  url={https://huggingface.co/videosdk-live/Namo-Turn-Detector-v1-Japanese},
+  note={ONNX-optimized DistilBERT for turn detection in Japanese}
+}
+```
+
+## 📄 License
+
+This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
+
+<div align="center">
+
+**Made with ❤️ by the VideoSDK Team**
+
+[![VideoSDK](https://img.shields.io/badge/VideoSDK-Live-blue)](https://videosdk.live)
+
+</div>

config.json

@@ -0,0 +1,29 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "class_weights": [
+    1.0,
+    1.0
+  ],
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.53.3",
+  "vocab_size": 119547
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c530c5392dc80fa247d42c4c9ca9b38f388c315483a8cbf879b251d13d0daf4
+size 541442940

model_quant.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812b282a64c3e4e308d5dd3ec63a45402d501d815880d4462059058dc596f552
+size 135967547

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}