About this model
Simultaneous speech translation between Chinese and English: it translates while you are still talking.
Official page · Weights · AI Search video at 10:02
Every size and format published by Tencent Hunyuan, largest first. Want one we don't host yet? Press Request: we add the most requested ones.
| Model | Parameters | Notes | |
|---|---|---|---|
| Hy-SimulMT 30B-A3B | 30.4B | BF16, translation only | |
| Hy-SimulMT 30B-A3B Interleave | 30.4B | BF16, transcript + translation | |
| Hy-SimulMT FP8 | 30.4B | 8-bit, translation only | |
| Hy-SimulMT Interleave FP8 | 30.4B | 8-bit, transcript + translation (prepared here) | |
| Hy-SimulMT GGUF | 30.4B | for llama.cpp |
Hy-SimulMT is an AI voice model by Tencent Hunyuan. Simultaneous speech translation between Chinese and English: it translates while you are still talking.
Not yet: Runs the official FP8 Interleave build with Tencent's SimulInfer pipeline: you get the transcript and the translation, with the moment each piece of translation was ready.
License: Apache-2.0. Commercial use of the outputs is allowed by the license.
In the AI Search video at 10:02.
All models · Not affiliated with Tencent Hunyuan or with AI Search.