---
title: S3-S2ST
canonical_url: "https://www.modelscope.cn/models/zhaoyx239/S3-S2ST"
md_url: "https://www.modelscope.cn/models/zhaoyx239/S3-S2ST.md"
repository: zhaoyx239/S3-S2ST
last_updated: 2026-11-12
parameters: 8.4B
tensor_type:
  - BF16
library_name:
  - onnx
  - safetensors
downloads: 5
stars: 0
tags:
  - speech-to-speech
  - translation
  - s3-s2st
---

# S3-S2ST

> S3-S2ST - zhaoyx239 在 ModelScope 开源的模型。4B models for Semantically Supervised Streaming Speech-to-Speech Translation.

- **Repository**: zhaoyx239/S3-S2ST
- **Parameters**: 8.4B
- **Tags**: speech-to-speech, translation, s3-s2st
- **Downloads**: 5
- **Stars**: 0
- **Last updated**: 2026-11-12

Source: https://www.modelscope.cn/models/zhaoyx239/S3-S2ST

---

# S3-S2ST

4B models for [Semantically Supervised Streaming Speech-to-Speech Translation](https://arxiv.org/abs/2610.36777).

[Code and installation](https://github.com/QwenAudio/S3-S2ST)

This repository provides two variants, each with its matching model weights and complete rendering assets:

| Directory | Model |
| --- | --- |
| `streaming/` | Streaming S2ST with READ/WRITE gate |
| `offline/` | Offline S2ST |

## Download and install

From the code checkout after installing the inference dependencies:

```bash
python tools/download_model.py --mode streaming --repo-id zhaoyx39/S3-S2ST --subfolder streaming
# Or the offline variant:
python tools/download_model.py --mode offline --repo-id zhaoyx39/S3-S2ST --subfolder offline
```

The installer downloads only the requested variant, verifies SHA256 and installs weights under `models/`. Follow the code README for audio preparation and inference commands. The model tensor values match the paper exports; paths are portable and no optimizer state, training data or experiment logs are included. Third-party terms are retained in each variant's `licenses/` directory and `THIRD_PARTY_NOTICES.md`.