Native audio in, structured decisions out. Aural One adapts Gemma 4 E2B to score supplied choices from a recording, a written state, and named questions. One model handles the audio and the decision; its inference path does not require speech-to-text or a separate sound classifier. This v0.1.0 research preview publishes a frozen adapter and 54.3 million updated acoustic/projection weights. The pinned Gemma 4 E2B base is downloaded separately. The language model was frozen during this final training stage. These numbers have different test scopes. The full evaluation report covers the frozen reference, listener-vote cross-entropy and calibration, same-words contrasts, sound events…
Open-weight model · Audio text to text
DuplexJev-32B-Para
by Adventists.ai adventists-ai/DuplexJev-32B-Para
DuplexJev-32B-Para is an open-weight model for audio text to text from Adventists.ai, released under Creative Commons Attribution-NonCommercial 4.0. Its published files total 7.0 GB.
Paper: arXiv:2610.02638 · Code: github.com/adventists-ai/duplexjev · Research note: teaching a speech-decision LLM to hear stress The DuplexJev model that hears the most beyond the words.
Parameters—
Context—
Weights7.0 GB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads—
Model Card
Paper: arXiv:2610.02638 · Code: github.com/adventists-ai/duplexjev · Research note: teaching a speech-decision LLM to hear stress The DuplexJev model that hears the most beyond the words. On top of everything DuplexJev-32B-Turn and DuplexJev-32B-Stress do (spoken QA, gender, emotion, turn-taking, stress and pauses), it also hears laughter, breathing, coughs and sighs, notices how someone is talking (whispering, shouting, very fast or slow), and can tell, roughly as a person would, whether two clips are the same speaker. Mandarin and English. DuplexJev reads typed, closed-set decisions from speech as a single-token distribution of the LLM: zero decode steps, many questions about the same…
Excerpt from the card by Adventists.ai, licensed cc-by-nc-4.0.
Identity and Version
- Repository
- adventists-ai/DuplexJev-32B-Para
- Publisher
- Adventists.ai
- Task
- Audio text to text
- Modality
- Other
- Library
- vllm
- Parameters
- Not stated by the source
- Languages
- zh, en
- Revision
- 66dc910fd5547d113d2a3a8700d73e059e45220c
- First published
- 2026-10-08
- Last updated
- 2026-10-09
Files and Weights
11 files, 7.0 GB in total. The weights are 2 files totalling 7.0 GB in safetensors.
Weights2 files · 7.0 GB
Configuration4 files · 145.7 KB
Tokenizer3 files · 14.2 MB
Documentation1 file · 7.3 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00015-of-00016.safetensors | Weights | 4.3 GB | 99ec6897fdb8 |
| model-00016-of-00016.safetensors | Weights | 2.7 GB | bf8951b041fd |
| model.safetensors.index.json | Configuration | 92.3 KB | — |
| normalizer.json | Configuration | 52.7 KB | — |
| preprocessor_config.json | Configuration | 356 B | — |
| special_tokens_map.json | Configuration | 355 B | — |
| README.md | Documentation | 7.3 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 0422f49acb9b |
| tokenizer_config.json | Tokenizer | 10.9 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 7.0 GB
Download from Adventists.ai
Released by Adventists.ai through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3-ASR-0.6B
- Described by arXiv:2610.02638
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About DuplexJev-32B-Para
Can I use DuplexJev-32B-Para commercially?
Not without separate permission. DuplexJev-32B-Para is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
Similar Models
Paper: arXiv:2610.02638 · Code: github.com/adventists-ai/duplexjev · Research note: teaching a speech-decision LLM to hear stress DuplexJev-32B-Turn that also hears stress and pauses. "I didn't say she took the money" and "I didn't say she took the money" are the same words. This model can tell them apart: it answers which word is stressed, is any word stressed at all, and where the speaker pauses, in Mandarin and English. Spoken QA, gender, emotion and turn-taking stay at the 32B-Turn level. Same size, same serving stack, same prompt format as the other DuplexJev models. DuplexJev reads typed, closed-set decisions from speech as a single-token distribution of the LLM: zero decode steps…
A small DuplexJev connector: the Whisper-small encoder (frozen) feeds a frozen SmolLM3-3B, and every typed question is read as a single-token distribution over its options, with zero decode steps and many questions per forward pass. Trained with the same recipe as the Qwen3-32B connectors released with the paper. The connector was trained with SmolLM3's no-think format (an empty block before the answer). The tokenizer in this repository carries that chat template; SmolLM3's default template adds a long system prompt with today's date and would not match. Leaderboard scores (see the GitHub README): main language (mean of qa100, ZJU-ML, Easy-Turn) 37.4, paralinguistics (mean of gender…
A small DuplexJev connector: the Whisper-small encoder (frozen) feeds a frozen Qwen3-4B-2507, and every typed question is read as a single-token distribution over its options, with zero decode steps and many questions per forward pass. Trained with the same recipe as the Qwen3-32B connectors released with the paper. Leaderboard scores (see the GitHub README): main language (mean of qa100, ZJU-ML, Easy-Turn) 53.5, paralinguistics (mean of gender, emotion) 43.0. Paper protocol: the evaluation prompts of the paper (single option order, one H200). duplexjev defaults: the package's own prompts with lang matched to the clip. Spoken QA with a small LLM is bounded by the LLM itself (see the…
MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness. It supports transcription and diarization across 50+ languages, single-pass inference on audio recordings up to 90 minutes long, and custom hotword prompting for domain-specific terms. Given an audio or video file, the model generates a compact speaker-aware transcript in one pass, including timestamps and anonymous speaker labels such as [S01], [S02], and beyond. 2026-07-22: The subtitle Web UI now supports both Simplified Chinese and English. 2026-07-14: MOSS-Transcribe-Diarize won first place in the 2nd MLC-SLM Challenge…
Sori-1B-MCQ — sori (소리) is Korean for sound — listens to a clip and answers typed questions about it: which of these options, how far along this scale, is this true. It returns the answer, a probability for every option you defined, and a confidence — never prose, never a token stream to parse. Code stays in charge: your program defines the options, reads the numbers and decides what to do. It is the decision model of the Sori Agent project at the Human Interface Lab, Seoul National University. Inspired by TypeSafe's System One model, Jev. Jev showed what a model built for software rather than for conversation looks like: a state, typed questions, calibrated probabilities, one call for many…