Upload V4 fine-tuned ONNX model

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+tags:
+- turn-detection
+- end-of-utterance
+- voice-agent
+- livekit
+- onnx
+---
+
+# Turn Detector V4 (Fine-tuned)
+
+This is a fine-tuned version of the LiveKit Turn Detector model, optimized for specific production use cases.
+
+## Model Description
+
+- **Base Model**: Qwen2-0.5B-Instruct
+- **Task**: End-of-Utterance (EOU) detection for voice agents
+- **Format**: ONNX (INT8 quantized)
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Training Data**: 1735 production conversation records
+
+## Performance
+
+- **Accuracy**: 79.25% @ threshold 0.38
+- **Dataset**: 1735 annotated production records
+- **Improvement**: +13.08% over LiveKit v1.2.2-en baseline
+
+## Usage
+
+```python
+from livekit.agents import turn_detector
+
+# Use with LiveKit agents
+detector = turn_detector.EOUModel.load(
+    model_id="Vurtnec/turn-detector",
+    download_files=["model.onnx"]
+)
+```
+
+## Model Files
+
+- `model.onnx`: ONNX Runtime optimized model (250MB)
+- Tokenizer files: Standard Qwen2 tokenizer configuration
+
+## Training Details
+
+- **Base Model**: LiveKit Turn Detector v1.2.2-en
+- **Fine-tuning Approach**: LoRA with rank=8, alpha=16
+- **Training Dataset**: 1735 production EOU examples
+- **Validation Split**: 10%
+- **Training Date**: December 2024
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{turn-detector-v4,
+  author = {Vurtnec},
+  title = {Turn Detector V4 - Fine-tuned EOU Model},
+  year = {2024},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/Vurtnec/turn-detector}}
+}
+```
+
+## License
+
+Apache 2.0

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|assistant|>": 49153,
+  "<|pad|>": 49154,
+  "<|user|>": 49152
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{'<|im_start|>' + '<|' + message['role'] + '|>' + message['content'] + '<|im_end|>'}}{% endfor %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7722e7cab7507e0ee5070adcd7cbc3c994edc3c11a098f1015cf43ef332f6b0
+size 262102331

ort_config.json

@@ -0,0 +1,22 @@
+{
+  "opset": 17,
+  "optimization": {
+    "enable_gelu_approximation": false,
+    "enable_gemm_fast_gelu": false,
+    "enable_layer_norm": true,
+    "enable_skip_layer_norm": true,
+    "enable_bias_skip_layer_norm": true,
+    "enable_bias_gelu": true,
+    "enable_gelu": true,
+    "enable_attention": true,
+    "use_multi_head_attention": true,
+    "enable_skip_simplified_layer_norm": true
+  },
+  "quantization": {
+    "format": "QOperator",
+    "mode": "IntegerOps",
+    "per_channel": false,
+    "reduce_range": true,
+    "weight_type": "QInt8"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|pad|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,182 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|pad|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}