GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
netease-youdao
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
netease-youdao
Model Tree
Qwen/Qwen2.5-14B
Input Modalities
Output Modalities
Supported Functionality
We evaluate Confucius4-T3PO on several public benchmarks for Chinese-to-English and English-to-Chinese simultaneous translation. We compare it against the open-source models InfiniSST and EAST, as well as two major commercial simultaneous translation systems, A and B.
The external comparison includes the low, native, and high quality–latency tiers.
As shown below, compared with standard GRPO, our training method more effectively explores and improves the quality–latency Pareto frontier. It also avoids extremely low-latency regimes in which translation quality collapses, maintaining training stability.
| Model | Hugging Face | ModelScope |
|---|---|---|
| Confucius4-T3PO | 🤗 Hugging Face | ModelScope |
| Confucius4-T3PO-GGUF | 🤗 Hugging Face | ModelScope |
The model maintains two pieces of state:
STREAMING_HISTORY holds the committed source–target pairs, formatted as
source_1¦target_1§source_2¦target_2§....CURRENT_INPUT holds the source buffer that has arrived but has not yet been
committed as a translation segment.The user message sent to the model consists of a task prompt and two labelled blocks:
text
{task_prompt}<STREAMING_HISTORY>{committed source-target pairs}<CURRENT_INPUT>{uncommitted source text}
Response handling is part of the model interface:
WAIT. Keep
CURRENT_INPUT and query again once more source text arrives.TRANS. Append the current source buffer and the
generated segment to the history, then clear the buffer.TRANS. Applications may choose to keep only the most recent history pairs.The environmental requirements for running it are exactly the same as those of the Qwen2.5-14B-Instruct model. Therefore, you can directly use Transformers or vLLM to load and run the model for inference. Below we provide only a brief guide to model deployment and inference; deploying it as a streaming simultaneous translation service involves context state maintenance and latency-tier selection, the implementation details of which can be found in the Confucius4-T3PO repository.
The following example uses the Hugging Face Transformers interface and shows a single decision step of the protocol:
bash
pip install torch transformers accelerate
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerMODEL_ID = "netease-youdao/Confucius4-T3PO"DIRECTION = "zh2en" # use "en2zh" for English-to-ChineseROLE = {"zh2en": "Chinese-to-English", "en2zh": "English-to-Chinese"}TARGET = {"zh2en": "English", "en2zh": "Chinese"}def task_prompt(direction: str) -> str:role, target = ROLE[direction], TARGET[direction]return (f"You are a professional {role} simultaneous interpreter.\n""The committed source-target pairs are in <STREAMING_HISTORY>, and ""the latest uncommitted source buffer is in <CURRENT_INPUT>. Output ""nothing if the context is ambiguous; otherwise output only the next "f"natural {target} translation segment, without explanations or markers.")tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained(MODEL_ID,torch_dtype="auto",device_map="auto",)model.eval()def infer_segment(history: str,current_input: str,*,direction: str = DIRECTION,force: bool = False,) -> tuple[str, str]:user_message = (f"{task_prompt(direction)}\n\n"f"<STREAMING_HISTORY>\n{history}\n\n"f"<CURRENT_INPUT>\n{current_input}")messages = [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": user_message},]prompt = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)with torch.inference_mode():outputs = model.generate(**inputs,max_new_tokens=128,# A forced segment must not come back empty. Requiring one new# token makes a WAIT response impossible at the sampling level,# which is more reliable than instructing the model not to wait.min_new_tokens=1 if force else 0,do_sample=False,pad_token_id=tokenizer.eos_token_id,)new_tokens = outputs[0, inputs["input_ids"].shape[-1] :]text = tokenizer.decode(new_tokens, skip_special_tokens=True).strip()text = text.replace("¦", "｜").replace("§", "；").strip()return ("WAIT", "") if not text else ("TRANS", text)history = ""current_input = "这个方法的核心思想是"action, segment = infer_segment(history, current_input)if action == "TRANS":history += f"{current_input}¦{segment}§"current_input = ""else:# On WAIT, keep current_input and query again after more source arrives.pass# At the end of the input stream, force-translate the remaining buffer.if current_input:action, segment = infer_segment(history, current_input, force=True)
Greedy decoding (
temperature=0) is recommended, because sampling can destabilize theWAIT/TRANSdecision and the segment boundaries.
bash
vllm serve netease-youdao/Confucius4-T3PO \--served-model-name Confucius4-T3PO \--dtype auto \--port 8010
Send the same chat messages and decoding settings through the OpenAI-compatible endpoint, preserving the STREAMING_HISTORY/CURRENT_INPUT state machine above. For how to maintain the context state (the handling of WAIT/TRANS, and the updating of history pairs and the buffer), please refer to the 3 Streaming Protocol section above.
bash
curl http://127.0.0.1:8010/v1/chat/completions \-H 'content-type: application/json' \-d '{"model": "Confucius4-T3PO","temperature": 0,"max_tokens": 128,"messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "<the task_prompt and the two blocks above, joined>"}]}'
This model is intended for live Chinese–English text or speech translation, where incremental output and bounded latency matter. Lower latency can reduce translation quality, because a committed segment is never revised when later context arrives. Performance on domains far from the training data, and on heavily disfluent ASR output, has not been fully characterized. Do not use the model without human review where errors could cause legal, medical, or safety consequences.
This model is released under the Apache License 2.0. Users must also comply with the licenses of the Qwen base model, the tokenizer, the training data, and any external ASR model used with it.
Join our community to ask questions, share ideas, and connect with other users and developers.
Scan the QR code below to join our WeChat group:
For high-concurrency, production-grade, domestically deployable, or private deployment solutions, as well as business inquiries and partnership opportunities, please feel free to contact us through the channels below.
We also welcome discussions in this repository’s Issues section. Feel free to ask questions, report bugs, or suggest improvements!
We will add formal citation information here once the technical report is released.
bibtex
@misc{Confucius4-T3PO,author = {NetEase Youdao Team},title = {Confucius4-T3PO: simulTaneous Translation via pareTo Policy Optimization},url = {},month = {Sep},year = {2026}}