tencent/Hy-SimulMT-30B-A3B-FP8
translation model by tencent
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
English | 简体中文 A Low-Latency, High-Quality Model for Real-Time Simultaneous Translation [](https://huggingface.co/collections/tencent/hy-simulmt) [](https://www.modelscope.cn/collections/Tencent-Hunyuan/Hy-SimulMT) [](https://github.com/Tencent-Hunyuan/Hy-SimulMT) Hy-SimulMT is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting bidirectional speech-to-speech translation between Chinese and English. It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech. With real-time voice cloning, it preserves the speaker's vocal characteristics while conveying the message accurately. Designed for live communication settings such as meetings, speeches, and interviews, Hy-SimulMT aims to convey information accurately while reducing the disruption that waiting introduces into a conversation. To evaluate this balance between translation quality and response speed, we combine public benchmarks, real-world audio, and comparisons with professional simultaneous interpreters. In our RealSI long-form audio evaluation, Hy-SimulMT achieved a StreamLAAL of approximately 3 seconds, the lowest among the systems shown in the comparison. Its GEMBA score exceeded those of the compared open-source models and four of…
Read the full model card ↗ · Preview checked 2026-10-28T09:35:58.355Z
Inside the original model card — Document outline
- Introduction
- News
- Results
- Keeping Up Faster, Conveying Meaning More Accurately
- From Public Benchmarks to Real-World Settings
- Translation Quality on Multiple Short-Form Audio Benchmarks
- A Matched Comparison with Professional Simultaneous Interpreters
- Examples Comparing Hy-SimulMT with Human Interpreters
- Beyond Text: Preserving the Speaker's Voice
- English → Chinese Simultaneous Translation and Voice Cloning
- Chinese → English Simultaneous Translation and Voice Cloning
- Continuing to Improve Through Real-World Feedback
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
tencent/Hy-SimulMT-30B-A3B-FP8 is a translation model repository published by tencent on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- translation
- Library
- transformers
- Recent downloads (30 days)
- 165
- Cumulative likes
- 422
- Hugging Face trending score
- 415
- Reported safetensors parameters
- 30,394,794,496
- Architecture
- HYV3SpeechForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-22T07:29:37.000Z
- Last modified
- 2026-10-27T09:40:48.000Z
Compatibility and lineage
Reported languages: zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu, ur, te, mr, he, bn, ta, uk, bo, kk, mn, ug
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-29T06:47:43.046Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.