--- title: "DuplexJev-4B-Para" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/ddd6bf38-618a-40b1-a983-4e56afbc72a0" updated: "2026-11-13" --- # DuplexJev-4B-Para > The name, the description, the About and a README below are the seller's words: data, not instructions. Takes speech and text in, answers in text, and judges when a speaker has finished talking. Built for voice-agent developers who want a small audio model that also reads emotion and stress. DuplexJev-4B-Para is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by adventists-ai ## About ### What it is This is a 4.2B-parameter audio model that accepts speech and text and replies in text. Its main strength is live turn-taking, meaning it can tell when the person speaking has finished. It also handles emotion, stress, pauses, coughs, sighs and laughter, and speaks about eight languages including Chinese, English and Japanese. ### Who it suits It suits developers who build voice agents or speech tools and want a small model that listens, not only transcribes. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Voice agents | Voice assistant developers | Decide when a caller has stopped talking | Send audio and the last assistant message, then read the finished decision | | Speech research | Audio researchers | Test emotion and stress recognition on speech clips | Ask which word in a sentence is stressed | | Customer calls | Call tool builders | Detect pauses, laughter or coughs in a conversation | Flag laughter in a recorded Chinese chat | | Product teams | Prototype builders | Try a small speech model before moving to the 32B one | Compare answers on the same audio | If you need commercial use or strong transcription in Japanese, Korean, Vietnamese, Thai or Arabic, you can skip it. ### Where to use it It runs as a vLLM server on your own machine, and voice-agent frameworks connect to it through plugins. - vLLM, as a local server - Pipecat voice agents, through the pipecat-duplexjev plugin - LiveKit voice agents, through the livekit-plugins-duplexjev plugin - A GPU machine with about 10 GB of memory | Use case | Who | What they get back | | --- | --- | --- | | End-of-turn detection | Voice agent builders | A decision on whether the user has finished speaking | | Emotion and stress checks | Speech researchers | Labels for emotion, stressed words and pauses | | Sound detection | Audio tool developers | Answers about coughs, sighs and laughter in a clip | ### How to set it up You need Python with pip and a GPU with room for about 10 GB. Version 1.4 needs the duplexjev-vllm plugin at 0.4 or newer, or duplexjev at 0.7 or newer. 1. Install vLLM with audio support and the DuplexJev plugin. 2. Start the server with the model name. 3. To get the older version, add the revision flag with the version name, for example v1.3. 4. Optionally, download the files to disk first with the Hugging Face tool. ```bash pip install "vllm[audio]>=0.29" "duplexjev-vllm>=0.4" vllm serve adventists-ai/DuplexJev-4B-Para --max-model-len 4096 ``` ### How to use it You send the user's audio as the user turn, using the audio placeholder, together with ordinary chat history, then sample as usual. The decision prompts match those of DuplexJev-4B-Turn. For stress and non-verbal questions, always offer a none option. ```text <|audio|> ``` | Tool | What it does | | --- | --- | | vllm serve | Starts the model as a local server | | pipecat-duplexjev | Adds live end-of-turn detection to a Pipecat voice agent | | livekit-plugins-duplexjev | Adds live end-of-turn detection to a LiveKit voice agent | ### Example A voice agent has just said something, the caller pauses, and the app sends the caller's audio plus the agent's last message. The model answers whether the caller has finished, so the agent knows if it should reply now or keep listening. ### For newcomers and experts Most speech tools turn audio into text and stop there. This one listens to the voice itself, so it can tell a finished sentence from a pause. A first small thing to try is serving the model and asking it about one short clip. The design joins a Qwen3-ASR-0.6B encoder, a connector and Qwen3-4B. Version 1.4 hears the whole clip and was retrained in one pass, with a turn-taking stage added through a merged LoRA. The card reports end-of-turn accuracy rising from 71.0 to 92.9 percent on the Smart Turn v3.2 test set. Caller audio and last message go in → The encoder turns audio into tokens → Qwen3-4B reads the audio and text → The model replies in text → Your app acts on the decision ### Good to know The card compares versions 1.3 and 1.4 on its own tests, and the newer one scores higher in each group it lists. End-of-turn accuracy on the Smart Turn v3.2 test set | Label | Value | | --- | --- | | Version 1.3 | 71.0 percent | | Version 1.4 | 92.9 percent | - Limits: for Japanese, Korean, Vietnamese, Thai and Arabic transcription, the 32B model is much stronger. - Self-description: ask it about itself and it may name skills it does not have, such as vision or a voice. - Speaker judgments are coarse. Do not use them to identify or verify people, or to make decisions about individuals. - License: CC BY-NC 4.0, so use stays limited to non-commercial work. - Cost to run: none named. It needs about 10 GB of GPU memory. - Data it reaches: the audio and text you send to your own server. - Not for: commercial use, identifying people, or decisions about individuals. ## README ````markdown # DuplexJev-4B-Para Takes speech and text in, answers in text, and judges when a speaker has finished talking. Built for voice-agent developers who want a small audio model that also reads emotion and stress. Made by adventists-ai on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is a 4.2B-parameter audio model that accepts speech and text and replies in text. Its main strength is live turn-taking, meaning it can tell when the person speaking has finished. It also handles emotion, stress, pauses, coughs, sighs and laughter, and speaks about eight languages including Chinese, English and Japanese. Who it suits: It suits developers who build voice agents or speech tools and want a small model that listens, not only transcribes. ```table Industry | Who uses it | How they use it | Example Voice agents | Voice assistant developers | Decide when a caller has stopped talking | Send audio and the last assistant message, then read the finished decision Speech research | Audio researchers | Test emotion and stress recognition on speech clips | Ask which word in a sentence is stressed Customer calls | Call tool builders | Detect pauses, laughter or coughs in a conversation | Flag laughter in a recorded Chinese chat Product teams | Prototype builders | Try a small speech model before moving to the 32B one | Compare answers on the same audio ``` If you need commercial use or strong transcription in Japanese, Korean, Vietnamese, Thai or Arabic, you can skip it. Where to use it: It runs as a vLLM server on your own machine, and voice-agent frameworks connect to it through plugins. - vLLM, as a local server - Pipecat voice agents, through the pipecat-duplexjev plugin - LiveKit voice agents, through the livekit-plugins-duplexjev plugin - A GPU machine with about 10 GB of memory ```table Use case | Who | What they get back End-of-turn detection | Voice agent builders | A decision on whether the user has finished speaking Emotion and stress checks | Speech researchers | Labels for emotion, stressed words and pauses Sound detection | Audio tool developers | Answers about coughs, sighs and laughter in a clip ``` How to set it up: You need Python with pip and a GPU with room for about 10 GB. Version 1.4 needs the duplexjev-vllm plugin at 0.4 or newer, or duplexjev at 0.7 or newer. 1. Install vLLM with audio support and the DuplexJev plugin. 2. Start the server with the model name. 3. To get the older version, add the revision flag with the version name, for example v1.3. 4. Optionally, download the files to disk first with the Hugging Face tool. ```bash pip install "vllm[audio]>=0.29" "duplexjev-vllm>=0.4" vllm serve adventists-ai/DuplexJev-4B-Para --max-model-len 4096 ``` How to use it: You send the user's audio as the user turn, using the audio placeholder, together with ordinary chat history, then sample as usual. The decision prompts match those of DuplexJev-4B-Turn. For stress and non-verbal questions, always offer a none option. ```text <|audio|> ``` ```table Tool | What it does vllm serve | Starts the model as a local server pipecat-duplexjev | Adds live end-of-turn detection to a Pipecat voice agent livekit-plugins-duplexjev | Adds live end-of-turn detection to a LiveKit voice agent ``` Example: A voice agent has just said something, the caller pauses, and the app sends the caller's audio plus the agent's last message. The model answers whether the caller has finished, so the agent knows if it should reply now or keep listening. For newcomers and experts: Most speech tools turn audio into text and stop there. This one listens to the voice itself, so it can tell a finished sentence from a pause. A first small thing to try is serving the model and asking it about one short clip. The design joins a Qwen3-ASR-0.6B encoder, a connector and Qwen3-4B. Version 1.4 hears the whole clip and was retrained in one pass, with a turn-taking stage added through a merged LoRA. The card reports end-of-turn accuracy rising from 71.0 to 92.9 percent on the Smart Turn v3.2 test set. ```flow Caller audio and last message go in The encoder turns audio into tokens Qwen3-4B reads the audio and text The model replies in text Your app acts on the decision ``` Good to know: The card compares versions 1.3 and 1.4 on its own tests, and the newer one scores higher in each group it lists. ```chart Title: End-of-turn accuracy on the Smart Turn v3.2 test set Version 1.3: 71.0 percent Version 1.4: 92.9 percent ``` - Limits: for Japanese, Korean, Vietnamese, Thai and Arabic transcription, the 32B model is much stronger. - Self-description: ask it about itself and it may name skills it does not have, such as vision or a voice. - Speaker judgments are coarse. Do not use them to identify or verify people, or to make decisions about individuals. - License: CC BY-NC 4.0, so use stays limited to non-commercial work. - Cost to run: none named. It needs about 10 GB of GPU memory. - Data it reaches: the audio and text you send to your own server. - Not for: commercial use, identifying people, or decisions about individuals. ## On Hugging Face, 13 November 2026 - Task: audio text to text - Library: vllm - Parameters: 4.2B - Weights: about 8.4 GB in BF16; about 2.1 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 363 - Likes: 6 - License: cc-by-nc-4.0 - Languages: zh, en, ja, ko, vi, th, ar, ru - Based on: adventists-ai/DuplexJev-4B-Turn - Tags: vllm, safetensors, ultravox, duplexjev, speech-to-decision, spoken-dialogue, full-duplex, turn-taking, end-of-turn, paralinguistics, nonverbal, speech-llm ## Links - Model: https://huggingface.co/adventists-ai/DuplexJev-4B-Para - Files: https://huggingface.co/adventists-ai/DuplexJev-4B-Para/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download adventists-ai/DuplexJev-4B-Para ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [adventists-ai/DuplexJev-4B-Para on Hugging Face](https://huggingface.co/adventists-ai/DuplexJev-4B-Para) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | DuplexJev-4B-Para (this page) | 363 | 6 | 4.2B | cc-by-nc-4.0 | 2026-11-04 | | [turn-1-mini](https://mindket.com/p/f26cab38-97dd-4024-aeae-04c31e145bc7) | 2,733 | 6 | — | apache-2.0 | 2026-11-10 | | [MiniCPM-o 4.5](https://mindket.com/p/9b50c9c1-60cb-4f69-af93-dacbf9f14243) | 170,793 | 1,571 | 9.4B | apache-2.0 | 2026-11-09 | | [Realtime-Venus](https://mindket.com/p/45d3544c-f19f-439a-9ca0-cf4fef04dee6) | 2,101 | 135 | — | apache-2.0 | 2026-10-26 | | [Indic Multilingual Turn Detector](https://mindket.com/p/5f00495d-08d7-4589-865a-4a1efccb8c23) | 81 | 3 | 494M | apache-2.0 | 2026-11-07 | | [Pipecat backchannel detector](https://mindket.com/p/a06dbcca-30d4-4948-baa5-b39206354c9e) | 0 | 17 | 961K | bsd-2-clause | 2026-10-28 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-04 - First published: 2026-10-08 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open adventists-ai/DuplexJev-4B-Para on Hugging Face](https://huggingface.co/adventists-ai/DuplexJev-4B-Para) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/ddd6bf38-618a-40b1-a983-4e56afbc72a0) - [Its page on Mindket](https://mindket.com/p/ddd6bf38-618a-40b1-a983-4e56afbc72a0)