Upload livekit-turn-detector

.gitattributes

@@ -44,3 +44,5 @@ embedding/blobs/f061cb7641880f52895cbacab7c4ab39b0844e2e6b73794f2798de460d9fa418
 embedding/blobs/f60256a833caee5c75a3903e589116752ee016ca7bc16f9b96e4db09984c5703 filter=lfs diff=lfs merge=lfs -text
 embedding/snapshots/835193815a3936a24a0ee7dc9e3d48c1fbb19c55/onnx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 embedding/snapshots/835193815a3936a24a0ee7dc9e3d48c1fbb19c55/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+livekit-turn-detector/blobs/2f7b4c93c1cdb6d1e858b01f63e5f0f15bdb979dd0d177e8996a244c80e03925 filter=lfs diff=lfs merge=lfs -text
+livekit-turn-detector/blobs/4e685767c3643b0363c9f826a98325683f29e9c7d550162c8e8740ba33aa31aa filter=lfs diff=lfs merge=lfs -text

livekit-turn-detector/blobs/03d79d95d1b482aa600d4af7649cb91eb4125eec

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

livekit-turn-detector/blobs/179ad5365c3b58dca5228ed0eb85552e5238d979

@@ -0,0 +1,115 @@
+LIVEKIT MODEL LICENSE AGREEMENT
+
+1. Introduction
+
+   LiveKit Incorporated ("LiveKit") is making available its proprietary models for
+   use pursuant to the terms and conditions of this Agreement. As further
+   described below, you may use these LiveKit models freely but can only use them
+   together with the LiveKit Agents framework. You cannot use the LiveKit models
+   on a standalone basis or with any other frameworks.
+
+   BY CLICKING "I ACCEPT," OR BY DOWNLOADING, INSTALLING, OR OTHERWISE ACCESSING
+   OR USING THE LIVEKIT MATERIALS, YOU AGREE THAT YOU HAVE READ AND UNDERSTOOD,
+   AND, AS A CONDITION TO YOUR USE OF THE LIVEKIT MATERIALS, YOU AGREE TO BE
+   BOUND BY, THE FOLLOWING TERMS AND CONDITIONS.
+
+2. Definitions
+
+   "Agreement" means this LiveKit Model License Agreement.
+
+   "Documentation" means the specifications, manuals, and documentation
+   accompanying any LiveKit Model and distributed by LiveKit.
+
+   "Licensee" or "you" means the individual or entity agreeing to be bound by
+   this Agreement.
+
+   "LiveKit Agents" means the proprietary LiveKit software framework for building
+   real-time multimodal AI applications with programmable backend participants.
+
+   "LiveKit Materials" means, collectively, the LiveKit Models and Documentation.
+
+   "LiveKit Model" means any of LiveKit's proprietary software models or
+   algorithms, including machine-learning software code, model weights,
+   inference-enabling software code, training-enabling software code, and
+   fine-tuning enabling software code. Any derivative works of a LiveKit Model,
+   whether developed by LiveKit, you, or any third party, will be deemed the
+   "LiveKit Model" for the purposes of this Agreement.
+
+3. License Rights
+
+   Right to Use LiveKit Materials. Subject to the terms and conditions of this
+   Agreement, including the requirements of Section 3.b, LiveKit grants you a
+   nonexclusive, nontransferable, worldwide, royalty-free license under LiveKit's
+   intellectual property rights to use, reproduce, distribute, copy, and create
+   derivative works of the LiveKit Materials.
+
+   Limitation on Use. As a condition to your use of the LiveKit Materials, you
+   agree: (i) not to use any LiveKit Models on a standalone basis or with any
+   frameworks other than LiveKit Agents; (ii) not to use any LiveKit Materials or
+   any output from, or results of using, LiveKit Models (including any derivative
+   works thereof) to improve or otherwise develop any other models that are not
+   LiveKit Models; or (iii) distribute or otherwise make available the LiveKit
+   Materials (including any derivative works thereof) except (x) pursuant to the
+   terms of this Agreement, and (y) you reproduce the above copyright notice.
+
+4. Intellectual Property
+
+   The LiveKit Materials are owned by LiveKit and its licensors. Except for the
+   rights granted to you under this Agreement, all rights are reserved and no
+   other express or implied rights are granted.
+
+   You will own any derivative works that you created from the LiveKit Materials,
+   subject to the terms of this Agreement.
+
+5. Disclaimer
+
+   UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, LIVEKIT PROVIDES
+   THE LIVEKIT MATERIALS, AND ANY OUTPUT OR RESULTS THEREFROM, ON AN "AS IS"
+   BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED,
+   INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE,
+   NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
+   ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
+   REDISTRIBUTING THE LIVEKIT MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
+   USE OF THE LIVEKIT MATERIALS AND ANY OUTPUT AND RESULTS.
+
+6. Limitation of Liability
+
+   IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE),
+   CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW (SUCH AS DELIBERATE
+   AND GROSSLY NEGLIGENT ACTS) OR AGREED TO IN WRITING, WILL LIVEKIT BE LIABLE TO
+   YOU FOR INDIRECT DAMAGES, INCLUDING ANY SPECIAL, INCIDENTAL, OR CONSEQUENTIAL
+   DAMAGES OF ANY CHARACTER ARISING AS A RESULT OF THIS AGREEMENT OR OUT OF THE
+   USE OR INABILITY TO USE THE LIVEKIT MATERIALS OR ANY OUTPUT OR RESULTS
+   THEREFROM (INCLUDING BUT NOT LIMITED TO DAMAGES FOR LOSS OF GOODWILL, WORK
+   STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL
+   DAMAGES OR LOSSES), EVEN IF LIVEKIT HAS BEEN ADVISED OF THE POSSIBILITY OF
+   SUCH DAMAGES.
+
+7. Trademarks
+
+   This Agreement does not grant permission to use the trade names, trademarks,
+   service marks, or product names of LiveKit, except as required for reasonable
+   and customary use in describing the origin of the LiveKit Materials.
+
+8. Term and Termination
+
+   The term of this Agreement commences upon your acceptance of this Agreement
+   and continues in effect until you cease using the LiveKit Materials or it is
+   terminated by either party (on immediate written notice to the other party).
+   This Agreement will automatically terminate if you breach any of its terms.
+   Upon termination, you must immediately cease all use of the LiveKit Materials.
+   Sections 4, 5, 6, and 9 will survive termination.
+
+9. Governing Law and Venue
+
+   This Agreement is subject to the laws of the State of California, without
+   regard to its conflict of laws principles. The UN Convention on Contracts for
+   the International Sale of Goods does not apply to this Agreement. The courts
+   located in San Francisco, California, have exclusive jurisdiction for any
+   dispute arising out of this Agreement.
+
++ + + +
+
+Last Updated: November 25, 2024
+
+

livekit-turn-detector/blobs/2f7b4c93c1cdb6d1e858b01f63e5f0f15bdb979dd0d177e8996a244c80e03925

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7b4c93c1cdb6d1e858b01f63e5f0f15bdb979dd0d177e8996a244c80e03925
+size 538095016

livekit-turn-detector/blobs/4e685767c3643b0363c9f826a98325683f29e9c7d550162c8e8740ba33aa31aa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e685767c3643b0363c9f826a98325683f29e9c7d550162c8e8740ba33aa31aa
+size 165035487

livekit-turn-detector/blobs/a0d1aa8a0fe51e70b4eea91a7f2621cbf4c18347

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.46.3"
+}

livekit-turn-detector/blobs/a1f02012c770e70739be68ede87513228a4cecbf

@@ -0,0 +1,172 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + '<|' + message['role'] + '|>' + message['content'] + '<|im_end|>'}}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

livekit-turn-detector/blobs/a6344aac8c09253b3b630fb776ae94478aa0275b

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

livekit-turn-detector/blobs/c2a58348e2cb8cc98e72a3db29c347dd9d961e28

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/tmp/tmpdhw4_gdh",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 49154
+}

livekit-turn-detector/blobs/db3ce48a6fcd0b741da0f6410866a77b1731d263

@@ -0,0 +1,185 @@
+---
+language:
+  - en
+  - es
+  - fr
+  - de
+  - it
+  - pt
+  - nl
+  - zh
+  - ja
+  - ko
+  - id
+  - tr
+  - ru
+  - hi
+license: other
+license_name: livekit-model-license
+license_link: LICENSE
+library_name: transformers
+pipeline_tag: text-classification
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+  - voice-ai
+  - turn-detection
+  - end-of-utterance
+  - end-of-turn
+  - conversational-ai
+  - livekit
+  - onnx
+  - quantized
+  - knowledge-distillation
+---
+
+# LiveKit Turn Detector
+
+An open-weights language model for contextually-aware end-of-utterance (EOU) detection in voice AI applications. The model predicts whether a user has finished speaking based on the semantic content of their transcribed speech, providing a critical complement to voice activity detection (VAD) systems.
+
+> **📖 For installation, usage examples, and integration guides, see the [LiveKit documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/).**
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Model Variants](#model-variants)
+- [How It Works](#how-it-works)
+- [Architecture and Training](#architecture-and-training)
+- [Supported Languages](#supported-languages)
+- [Benchmarks](#benchmarks)
+- [Usage](#usage)
+- [Deployment Requirements](#deployment-requirements)
+- [Limitations](#limitations)
+- [License](LICENSE)
+- [Resources](#resources)
+
+## Overview
+
+Traditional voice agents rely on voice activity detection (VAD) to determine when a user has finished speaking. VAD works by detecting the presence or absence of speech in an audio signal and applying a silence timer. While effective for detecting pauses, VAD lacks language understanding and frequently causes false positives. For example, a user who says *"I need to think about that for a moment..."* and then pauses will be interrupted by a VAD-only system, even though they clearly intend to continue.
+
+This model adds semantic understanding to the turn detection process. It analyzes the transcribed text of a conversation in real time and predicts the probability that the user has completed their turn. When integrated into a voice pipeline alongside VAD, it substantially reduces unwanted interruptions while maintaining responsiveness.
+
+The model is particularly effective in scenarios involving structured data input — such as dictating addresses, phone numbers, email addresses, and credit card numbers — where natural pauses between segments do not indicate completion.
+
+## Model Variants
+
+**Multilingual** (recommended) and  **English-only** (deprecated) are distributed as INT8 quantized ONNX models (`model_q8.onnx`) optimized for CPU inference.
+
+> **⚠️ The English-only model (`EnglishModel`) is deprecated.** Use the **multilingual model (`MultilingualModel`)** for all new projects, including English-only applications. The multilingual model provides better accuracy across all languages — including English — thanks to knowledge distillation from a larger teacher model and an expanded training dataset. The English-only variant will not receive further updates.
+
+## How It Works
+
+The model operates on transcribed text from a speech-to-text (STT) system, not raw audio.
+
+1. **Input**: The recent conversation history (up to **6 turns**, truncated to **128 tokens**) is formatted using the [Qwen chat template](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) with `<|im_start|>` / `<|im_end|>` delimiters. The final user message is left *without* the closing `<|im_end|>` token.
+
+2. **Prediction**: The model predicts the probability of the `<|im_end|>` token appearing next. A **high probability** indicates the user has likely finished their utterance. A **low probability** indicates they are likely to continue.
+
+3. **Thresholding**: Per-language thresholds (stored in `languages.json`) convert the raw probability into a binary decision. These thresholds are tuned to balance responsiveness and accuracy for each supported language.
+
+4. **Integration with VAD**: In the LiveKit Agents framework, the model works alongside the [Silero VAD](https://docs.livekit.io/agents/logic/turns/vad/) plugin. VAD handles speech presence detection and interruption triggering, while this model provides the semantic signal for when to commit a turn.
+
+### Text Preprocessing
+
+The **multilingual** variant applies the following normalization before inference:
+
+- NFKC unicode normalization
+- Lowercasing
+- Punctuation removal (preserving apostrophes and hyphens)
+- Whitespace collapsing
+
+The **English-only** variant passes raw transcribed text without normalization.
+
+## Architecture and Training
+
+### Base Model
+
+Both variants are fine-tuned from [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct), selected for its strong performance on this task while enabling low-latency CPU inference.
+
+### Knowledge Distillation
+
+A **Qwen2.5-7B-Instruct** model was first fine-tuned as a teacher on end-of-turn prediction. Its knowledge was then distilled into the 0.5B student model. The distilled model approaches teacher-level accuracy while maintaining the efficiency of the smaller architecture, converging after approximately 1,500 training steps.
+
+### Training Data
+
+The training dataset is a mix of:
+
+- **Real call center transcripts** covering diverse conversational patterns
+- **Synthetic dialogues** emphasizing structured data input — addresses, email addresses, phone numbers, and credit card numbers
+- **Multi-format STT outputs** to handle provider variation (e.g., "forty two" vs. "42"), ensuring consistent predictions across different STT engines without runtime overhead
+
+Although structured data enhancements were added only to the English training set, performance improvements generalized across languages due to the multilingual knowledge encoded in the Qwen2.5 base model.
+
+### Quantization
+
+The trained model is exported to ONNX format and quantized to INT8 (`model_q8.onnx`), enabling efficient CPU-only inference with ONNX Runtime.
+
+## Supported Languages
+
+The multilingual model supports 14 languages. The model relies on the STT provider to report the detected language, which is then used to select the appropriate per-language threshold.
+
+English, Spanish, French, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Indonesian, Turkish, Russian, Hindi
+
+## Benchmarks
+
+### Detection Accuracy (Multilingual Variant)
+
+- **True positive** — the model correctly identifies the user has finished speaking.
+- **True negative** — the model correctly identifies the user will continue speaking.
+
+| Language | True Positive Rate | True Negative Rate |
+|---|---|---|
+| Hindi | 99.4% | 96.3% |
+| Korean | 99.3% | 94.5% |
+| French | 99.3% | 88.9% |
+| Indonesian | 99.3% | 89.4% |
+| Japanese | 99.3% | 88.8% |
+| Dutch | 99.3% | 88.1% |
+| Russian | 99.3% | 88.0% |
+| German | 99.3% | 87.8% |
+| Portuguese | 99.4% | 87.4% |
+| Turkish | 99.3% | 87.3% |
+| English | 99.3% | 87.0% |
+| Chinese | 99.3% | 86.6% |
+| Spanish | 99.3% | 86.0% |
+| Italian | 99.3% | 85.1% |
+
+### Improvement Over Prior Version
+
+The multilingual v0.4.1 release achieved a **39.23% relative improvement** in handling structured inputs (emails, addresses, phone numbers, credit card numbers) compared to the prior version, reducing premature interruptions during data collection scenarios.
+
+## Usage
+
+The model is designed for use as a turn detection plugin within the [LiveKit Agents](https://github.com/livekit/agents) framework.
+
+For complete installation instructions, code examples (Python and Node.js), and configuration options, see the **[LiveKit turn detector plugin documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/)**.
+
+For broader context on how turn detection fits into the voice pipeline — including VAD configuration, interruption handling, and manual turn control — see the **[Turns overview](https://docs.livekit.io/agents/logic/turns/)**.
+
+## Deployment Requirements
+
+- **Runtime**: CPU-only (no GPU required). Uses [ONNX Runtime](https://onnxruntime.ai/) with the `CPUExecutionProvider`.
+- **RAM**: <500 MB for the multilingual model.
+- **Instance type**: Use compute-optimized instances (e.g., AWS c6i, c7i). Avoid burstable instances (e.g., AWS t3, t4g) to prevent inference timeouts from CPU credit exhaustion.
+- **LiveKit Cloud**: The model is deployed globally on LiveKit Cloud. Agents running there automatically use the optimized remote inference service with no local resource requirements.
+
+## Limitations
+
+- **Text-only input**: The model operates on STT-transcribed text and cannot incorporate prosodic cues such as pauses, intonation, or emphasis. Future versions may integrate multimodal audio features.
+- **STT dependency**: Prediction quality depends on the accuracy and output format of the upstream STT provider. Mismatches between training and deployment STT formats may degrade performance.
+- **Context window**: Limited to 128 tokens across a maximum of 6 conversation turns.
+- **Language coverage**: Currently supports 14 languages. Performance on unsupported languages is undefined.
+- **Realtime model compatibility**: Cannot be used with audio-native realtime models (e.g., OpenAI Realtime API) without adding a separate STT service, which incurs additional cost and latency.
+
+## License
+
+This model is released under the [LiveKit Model License](./LICENSE).
+
+## Resources
+
+- **[Documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/)**: Full plugin documentation, installation, and integration guide.
+- **[Turns Overview](https://docs.livekit.io/agents/logic/turns/)**: How turn detection fits into the LiveKit Agents voice pipeline.
+- **[Blog: Improved End-of-Turn Model](https://blog.livekit.io/improved-end-of-turn-model-cuts-voice-ai-interruptions-39/)**: Technical deep dive on the multilingual distillation approach and benchmarks.
+- **[Blog: Using a Transformer for Turn Detection](https://blog.livekit.io/using-a-transformer-to-improve-end-of-turn-detection/)**: Original blog post introducing the concept and architecture.
+- **[Video: LiveKit Turn Detector](https://youtu.be/OZG0oZKctgw)**: Overview video demonstrating the plugin.
+- **[GitHub: Plugin Source](https://github.com/livekit/agents/tree/main/livekit-plugins/livekit-plugins-turn-detector)**: Source code for the `livekit-plugins-turn-detector` package.
+- **[PyPI](https://pypi.org/project/livekit-plugins-turn-detector/)** | **[npm](https://www.npmjs.com/package/@livekit/agents-plugin-livekit)**: Package registries.

livekit-turn-detector/blobs/ef52d45d1c6f53be3d8ee6091be8cdf6a702d996

@@ -0,0 +1,4 @@
+{
+  "<|assistant|>": 49153,
+  "<|user|>": 49152
+}

livekit-turn-detector/blobs/ff763bc19f24aaef5ff45e25dc6c21ce095c2d79

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

livekit-turn-detector/refs/main

@@ -0,0 +1 @@
+fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/LICENSE

@@ -0,0 +1,115 @@
+LIVEKIT MODEL LICENSE AGREEMENT
+
+1. Introduction
+
+   LiveKit Incorporated ("LiveKit") is making available its proprietary models for
+   use pursuant to the terms and conditions of this Agreement. As further
+   described below, you may use these LiveKit models freely but can only use them
+   together with the LiveKit Agents framework. You cannot use the LiveKit models
+   on a standalone basis or with any other frameworks.
+
+   BY CLICKING "I ACCEPT," OR BY DOWNLOADING, INSTALLING, OR OTHERWISE ACCESSING
+   OR USING THE LIVEKIT MATERIALS, YOU AGREE THAT YOU HAVE READ AND UNDERSTOOD,
+   AND, AS A CONDITION TO YOUR USE OF THE LIVEKIT MATERIALS, YOU AGREE TO BE
+   BOUND BY, THE FOLLOWING TERMS AND CONDITIONS.
+
+2. Definitions
+
+   "Agreement" means this LiveKit Model License Agreement.
+
+   "Documentation" means the specifications, manuals, and documentation
+   accompanying any LiveKit Model and distributed by LiveKit.
+
+   "Licensee" or "you" means the individual or entity agreeing to be bound by
+   this Agreement.
+
+   "LiveKit Agents" means the proprietary LiveKit software framework for building
+   real-time multimodal AI applications with programmable backend participants.
+
+   "LiveKit Materials" means, collectively, the LiveKit Models and Documentation.
+
+   "LiveKit Model" means any of LiveKit's proprietary software models or
+   algorithms, including machine-learning software code, model weights,
+   inference-enabling software code, training-enabling software code, and
+   fine-tuning enabling software code. Any derivative works of a LiveKit Model,
+   whether developed by LiveKit, you, or any third party, will be deemed the
+   "LiveKit Model" for the purposes of this Agreement.
+
+3. License Rights
+
+   Right to Use LiveKit Materials. Subject to the terms and conditions of this
+   Agreement, including the requirements of Section 3.b, LiveKit grants you a
+   nonexclusive, nontransferable, worldwide, royalty-free license under LiveKit's
+   intellectual property rights to use, reproduce, distribute, copy, and create
+   derivative works of the LiveKit Materials.
+
+   Limitation on Use. As a condition to your use of the LiveKit Materials, you
+   agree: (i) not to use any LiveKit Models on a standalone basis or with any
+   frameworks other than LiveKit Agents; (ii) not to use any LiveKit Materials or
+   any output from, or results of using, LiveKit Models (including any derivative
+   works thereof) to improve or otherwise develop any other models that are not
+   LiveKit Models; or (iii) distribute or otherwise make available the LiveKit
+   Materials (including any derivative works thereof) except (x) pursuant to the
+   terms of this Agreement, and (y) you reproduce the above copyright notice.
+
+4. Intellectual Property
+
+   The LiveKit Materials are owned by LiveKit and its licensors. Except for the
+   rights granted to you under this Agreement, all rights are reserved and no
+   other express or implied rights are granted.
+
+   You will own any derivative works that you created from the LiveKit Materials,
+   subject to the terms of this Agreement.
+
+5. Disclaimer
+
+   UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, LIVEKIT PROVIDES
+   THE LIVEKIT MATERIALS, AND ANY OUTPUT OR RESULTS THEREFROM, ON AN "AS IS"
+   BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED,
+   INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE,
+   NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
+   ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
+   REDISTRIBUTING THE LIVEKIT MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
+   USE OF THE LIVEKIT MATERIALS AND ANY OUTPUT AND RESULTS.
+
+6. Limitation of Liability
+
+   IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE),
+   CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW (SUCH AS DELIBERATE
+   AND GROSSLY NEGLIGENT ACTS) OR AGREED TO IN WRITING, WILL LIVEKIT BE LIABLE TO
+   YOU FOR INDIRECT DAMAGES, INCLUDING ANY SPECIAL, INCIDENTAL, OR CONSEQUENTIAL
+   DAMAGES OF ANY CHARACTER ARISING AS A RESULT OF THIS AGREEMENT OR OUT OF THE
+   USE OR INABILITY TO USE THE LIVEKIT MATERIALS OR ANY OUTPUT OR RESULTS
+   THEREFROM (INCLUDING BUT NOT LIMITED TO DAMAGES FOR LOSS OF GOODWILL, WORK
+   STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL
+   DAMAGES OR LOSSES), EVEN IF LIVEKIT HAS BEEN ADVISED OF THE POSSIBILITY OF
+   SUCH DAMAGES.
+
+7. Trademarks
+
+   This Agreement does not grant permission to use the trade names, trademarks,
+   service marks, or product names of LiveKit, except as required for reasonable
+   and customary use in describing the origin of the LiveKit Materials.
+
+8. Term and Termination
+
+   The term of this Agreement commences upon your acceptance of this Agreement
+   and continues in effect until you cease using the LiveKit Materials or it is
+   terminated by either party (on immediate written notice to the other party).
+   This Agreement will automatically terminate if you breach any of its terms.
+   Upon termination, you must immediately cease all use of the LiveKit Materials.
+   Sections 4, 5, 6, and 9 will survive termination.
+
+9. Governing Law and Venue
+
+   This Agreement is subject to the laws of the State of California, without
+   regard to its conflict of laws principles. The UN Convention on Contracts for
+   the International Sale of Goods does not apply to this Agreement. The courts
+   located in San Francisco, California, have exclusive jurisdiction for any
+   dispute arising out of this Agreement.
+
++ + + +
+
+Last Updated: November 25, 2024
+
+

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/README.md

@@ -0,0 +1,185 @@
+---
+language:
+  - en
+  - es
+  - fr
+  - de
+  - it
+  - pt
+  - nl
+  - zh
+  - ja
+  - ko
+  - id
+  - tr
+  - ru
+  - hi
+license: other
+license_name: livekit-model-license
+license_link: LICENSE
+library_name: transformers
+pipeline_tag: text-classification
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+  - voice-ai
+  - turn-detection
+  - end-of-utterance
+  - end-of-turn
+  - conversational-ai
+  - livekit
+  - onnx
+  - quantized
+  - knowledge-distillation
+---
+
+# LiveKit Turn Detector
+
+An open-weights language model for contextually-aware end-of-utterance (EOU) detection in voice AI applications. The model predicts whether a user has finished speaking based on the semantic content of their transcribed speech, providing a critical complement to voice activity detection (VAD) systems.
+
+> **📖 For installation, usage examples, and integration guides, see the [LiveKit documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/).**
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Model Variants](#model-variants)
+- [How It Works](#how-it-works)
+- [Architecture and Training](#architecture-and-training)
+- [Supported Languages](#supported-languages)
+- [Benchmarks](#benchmarks)
+- [Usage](#usage)
+- [Deployment Requirements](#deployment-requirements)
+- [Limitations](#limitations)
+- [License](LICENSE)
+- [Resources](#resources)
+
+## Overview
+
+Traditional voice agents rely on voice activity detection (VAD) to determine when a user has finished speaking. VAD works by detecting the presence or absence of speech in an audio signal and applying a silence timer. While effective for detecting pauses, VAD lacks language understanding and frequently causes false positives. For example, a user who says *"I need to think about that for a moment..."* and then pauses will be interrupted by a VAD-only system, even though they clearly intend to continue.
+
+This model adds semantic understanding to the turn detection process. It analyzes the transcribed text of a conversation in real time and predicts the probability that the user has completed their turn. When integrated into a voice pipeline alongside VAD, it substantially reduces unwanted interruptions while maintaining responsiveness.
+
+The model is particularly effective in scenarios involving structured data input — such as dictating addresses, phone numbers, email addresses, and credit card numbers — where natural pauses between segments do not indicate completion.
+
+## Model Variants
+
+**Multilingual** (recommended) and  **English-only** (deprecated) are distributed as INT8 quantized ONNX models (`model_q8.onnx`) optimized for CPU inference.
+
+> **⚠️ The English-only model (`EnglishModel`) is deprecated.** Use the **multilingual model (`MultilingualModel`)** for all new projects, including English-only applications. The multilingual model provides better accuracy across all languages — including English — thanks to knowledge distillation from a larger teacher model and an expanded training dataset. The English-only variant will not receive further updates.
+
+## How It Works
+
+The model operates on transcribed text from a speech-to-text (STT) system, not raw audio.
+
+1. **Input**: The recent conversation history (up to **6 turns**, truncated to **128 tokens**) is formatted using the [Qwen chat template](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) with `<|im_start|>` / `<|im_end|>` delimiters. The final user message is left *without* the closing `<|im_end|>` token.
+
+2. **Prediction**: The model predicts the probability of the `<|im_end|>` token appearing next. A **high probability** indicates the user has likely finished their utterance. A **low probability** indicates they are likely to continue.
+
+3. **Thresholding**: Per-language thresholds (stored in `languages.json`) convert the raw probability into a binary decision. These thresholds are tuned to balance responsiveness and accuracy for each supported language.
+
+4. **Integration with VAD**: In the LiveKit Agents framework, the model works alongside the [Silero VAD](https://docs.livekit.io/agents/logic/turns/vad/) plugin. VAD handles speech presence detection and interruption triggering, while this model provides the semantic signal for when to commit a turn.
+
+### Text Preprocessing
+
+The **multilingual** variant applies the following normalization before inference:
+
+- NFKC unicode normalization
+- Lowercasing
+- Punctuation removal (preserving apostrophes and hyphens)
+- Whitespace collapsing
+
+The **English-only** variant passes raw transcribed text without normalization.
+
+## Architecture and Training
+
+### Base Model
+
+Both variants are fine-tuned from [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct), selected for its strong performance on this task while enabling low-latency CPU inference.
+
+### Knowledge Distillation
+
+A **Qwen2.5-7B-Instruct** model was first fine-tuned as a teacher on end-of-turn prediction. Its knowledge was then distilled into the 0.5B student model. The distilled model approaches teacher-level accuracy while maintaining the efficiency of the smaller architecture, converging after approximately 1,500 training steps.
+
+### Training Data
+
+The training dataset is a mix of:
+
+- **Real call center transcripts** covering diverse conversational patterns
+- **Synthetic dialogues** emphasizing structured data input — addresses, email addresses, phone numbers, and credit card numbers
+- **Multi-format STT outputs** to handle provider variation (e.g., "forty two" vs. "42"), ensuring consistent predictions across different STT engines without runtime overhead
+
+Although structured data enhancements were added only to the English training set, performance improvements generalized across languages due to the multilingual knowledge encoded in the Qwen2.5 base model.
+
+### Quantization
+
+The trained model is exported to ONNX format and quantized to INT8 (`model_q8.onnx`), enabling efficient CPU-only inference with ONNX Runtime.
+
+## Supported Languages
+
+The multilingual model supports 14 languages. The model relies on the STT provider to report the detected language, which is then used to select the appropriate per-language threshold.
+
+English, Spanish, French, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Indonesian, Turkish, Russian, Hindi
+
+## Benchmarks
+
+### Detection Accuracy (Multilingual Variant)
+
+- **True positive** — the model correctly identifies the user has finished speaking.
+- **True negative** — the model correctly identifies the user will continue speaking.
+
+| Language | True Positive Rate | True Negative Rate |
+|---|---|---|
+| Hindi | 99.4% | 96.3% |
+| Korean | 99.3% | 94.5% |
+| French | 99.3% | 88.9% |
+| Indonesian | 99.3% | 89.4% |
+| Japanese | 99.3% | 88.8% |
+| Dutch | 99.3% | 88.1% |
+| Russian | 99.3% | 88.0% |
+| German | 99.3% | 87.8% |
+| Portuguese | 99.4% | 87.4% |
+| Turkish | 99.3% | 87.3% |
+| English | 99.3% | 87.0% |
+| Chinese | 99.3% | 86.6% |
+| Spanish | 99.3% | 86.0% |
+| Italian | 99.3% | 85.1% |
+
+### Improvement Over Prior Version
+
+The multilingual v0.4.1 release achieved a **39.23% relative improvement** in handling structured inputs (emails, addresses, phone numbers, credit card numbers) compared to the prior version, reducing premature interruptions during data collection scenarios.
+
+## Usage
+
+The model is designed for use as a turn detection plugin within the [LiveKit Agents](https://github.com/livekit/agents) framework.
+
+For complete installation instructions, code examples (Python and Node.js), and configuration options, see the **[LiveKit turn detector plugin documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/)**.
+
+For broader context on how turn detection fits into the voice pipeline — including VAD configuration, interruption handling, and manual turn control — see the **[Turns overview](https://docs.livekit.io/agents/logic/turns/)**.
+
+## Deployment Requirements
+
+- **Runtime**: CPU-only (no GPU required). Uses [ONNX Runtime](https://onnxruntime.ai/) with the `CPUExecutionProvider`.
+- **RAM**: <500 MB for the multilingual model.
+- **Instance type**: Use compute-optimized instances (e.g., AWS c6i, c7i). Avoid burstable instances (e.g., AWS t3, t4g) to prevent inference timeouts from CPU credit exhaustion.
+- **LiveKit Cloud**: The model is deployed globally on LiveKit Cloud. Agents running there automatically use the optimized remote inference service with no local resource requirements.
+
+## Limitations
+
+- **Text-only input**: The model operates on STT-transcribed text and cannot incorporate prosodic cues such as pauses, intonation, or emphasis. Future versions may integrate multimodal audio features.
+- **STT dependency**: Prediction quality depends on the accuracy and output format of the upstream STT provider. Mismatches between training and deployment STT formats may degrade performance.
+- **Context window**: Limited to 128 tokens across a maximum of 6 conversation turns.
+- **Language coverage**: Currently supports 14 languages. Performance on unsupported languages is undefined.
+- **Realtime model compatibility**: Cannot be used with audio-native realtime models (e.g., OpenAI Realtime API) without adding a separate STT service, which incurs additional cost and latency.
+
+## License
+
+This model is released under the [LiveKit Model License](./LICENSE).
+
+## Resources
+
+- **[Documentation](https://docs.livekit.io/agents/logic/turns/turn-detector/)**: Full plugin documentation, installation, and integration guide.
+- **[Turns Overview](https://docs.livekit.io/agents/logic/turns/)**: How turn detection fits into the LiveKit Agents voice pipeline.
+- **[Blog: Improved End-of-Turn Model](https://blog.livekit.io/improved-end-of-turn-model-cuts-voice-ai-interruptions-39/)**: Technical deep dive on the multilingual distillation approach and benchmarks.
+- **[Blog: Using a Transformer for Turn Detection](https://blog.livekit.io/using-a-transformer-to-improve-end-of-turn-detection/)**: Original blog post introducing the concept and architecture.
+- **[Video: LiveKit Turn Detector](https://youtu.be/OZG0oZKctgw)**: Overview video demonstrating the plugin.
+- **[GitHub: Plugin Source](https://github.com/livekit/agents/tree/main/livekit-plugins/livekit-plugins-turn-detector)**: Source code for the `livekit-plugins-turn-detector` package.
+- **[PyPI](https://pypi.org/project/livekit-plugins-turn-detector/)** | **[npm](https://www.npmjs.com/package/@livekit/agents-plugin-livekit)**: Package registries.

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|assistant|>": 49153,
+  "<|user|>": 49152
+}

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/tmp/tmpdhw4_gdh",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 49154
+}

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.46.3"
+}

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7b4c93c1cdb6d1e858b01f63e5f0f15bdb979dd0d177e8996a244c80e03925
+size 538095016

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/model_q8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e685767c3643b0363c9f826a98325683f29e9c7d550162c8e8740ba33aa31aa
+size 165035487

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e685767c3643b0363c9f826a98325683f29e9c7d550162c8e8740ba33aa31aa
+size 165035487

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "use_external_data_format": false
+}

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

livekit-turn-detector/snapshots/fba34c38ad5d30a63ebb83a9e6bf271cf4c91d67/tokenizer_config.json

@@ -0,0 +1,172 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + '<|' + message['role'] + '|>' + message['content'] + '<|im_end|>'}}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}