GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
adventists-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
adventists-ai
Model Tree
Qwen/Qwen3-32B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install "duplexjev[speech]>=0.2.1"python
from duplexjev import Decider, Question d = Decider.from_pretrained("adventists-ai/DuplexJev-A-Gender-Qwen3-ASR-0.6B-Qwen3-32B", device="auto") # Qwen3-32B bf16: ~65 GB of GPU memory # English clipd.decide("utterance_en.wav", [ Question("gender", "What is the perceived gender of the speaker?", ["female", "male"], lang="en"),], lang="en")# Chinese clip: ask in Chinese, with Chinese optionsd.decide("utterance_zh.wav", [ Question("gender", "说话人的性别是？", ["男性", "女性"], lang="zh"),], lang="zh")# -> {question_id: {"answer": ..., "confidence": ..., "probs": {option: p, ...}}}Ask in the language of the clip, with options worded as in the examples: the connector was trained with
language-matched prompts. Use duplexjev>=0.2.1; 0.2.0 padded audio at the start, which costs several points.
Already have local copies of the encoder and LLM? Pass text_model="/path/Qwen3-32B" and
audio_model="/path/Qwen3-ASR-0.6B-Encoder-XAttn"; this works offline.
decide_batch answers question groups over many clips in one pass. See the GitHub repository for the
batched pipeline, prefix sharing, the serving loop and evaluation scripts.
| Evaluation | Score (%) |
|---|---|
| Gender, 800 real utterances | 89.4 |
| ZJU gender benchmark (native / lettered prompt) | 73 / 67 |
| qa100 | 86 (+3 vs. R2) |
| ZJU-ML | 79 (+2 vs. R2) |
qa100: 100 bilingual spoken multiple-choice questions (adventists-ai/qa100).
ZJU-ML: main-language part of the ZJU audio benchmark v2.0.0 (50 real-speech factual + 50 TTS math/logic items).
Numbers are single-token readouts with the paper's evaluation prompts.
Reproduced with duplexjev 0.2.1 and its default prompts (one option order, lang matched to the clip):
| Evaluation | Score (%) |
|---|---|
| Gender, 800 real utterances | 89.2 |
| Emotion, 4-way, 800 utterances | 27.1 |
| qa100 | 85 |
Apache-2.0 for the connector weights and code in this repository. The frozen base models keep their own licences (Qwen3-32B and Qwen3-ASR-0.6B: Apache-2.0). The training corpora have their own terms, and some of them (e.g. WenetSpeech, CoVoST 2) are licensed for non-commercial use only; check them before commercial use.
bibtex
@inproceedings{jin2027duplexjev, title = {Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen {LLM} Hear Beyond the Transcript}, author = {Jin, Jie and Ma, Ziyin and Yin, Min and Chen, Jinyu and Song, Haigang and Pang, Zhikun and Zhang, Xiaowen}, booktitle = {Submitted to IEEE ICASSP}, year = {2027}}Built by Adventists.ai. Claude (Anthropic) assisted with code.
from duplexjev import Decider, Question d = Decider.from_pretrained("adventists-ai/DuplexJev-A-Gender-Qwen3-ASR-0.6B-Qwen3-32B", device="auto") # Qwen3-32B bf16: ~65 GB of GPU memory # English clipd.decide("utterance_en.wav", [ Question("gender", "What is the perceived gender of the speaker?", ["female", "male"], lang="en"),], lang="en")# Chinese clip: ask in Chinese, with Chinese optionsd.decide("utterance_zh.wav", [ Question("gender", "说话人的性别是？", ["男性", "女性"], lang="zh"),], lang="zh")# -> {question_id: {"answer": ..., "confidence": ..., "probs": {option: p, ...}}}@inproceedings{jin2027duplexjev, title = {Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen {LLM} Hear Beyond the Transcript}, author = {Jin, Jie and Ma, Ziyin and Yin, Min and Chen, Jinyu and Song, Haigang and Pang, Zhikun and Zhang, Xiaowen}, booktitle = {Submitted to IEEE ICASSP}, year = {2027}}