---
title: SenseVoiceSmall-INT8-ONNX
canonical_url: "https://www.modelscope.cn/models/nocmtone/SenseVoiceSmall-INT8-ONNX"
md_url: "https://www.modelscope.cn/models/nocmtone/SenseVoiceSmall-INT8-ONNX.md"
repository: nocmtone/SenseVoiceSmall-INT8-ONNX
chinese_name: SenseVoiceSmall-INT8-ONNX
last_updated: 2026-09-17
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - iic/SenseVoiceSmall
base_model_relation: finetune
library_name:
  - onnx
downloads: 0
stars: 0
tags:
  - asr
  - onnx
  - int8
  - sherpa-onnx
  - speech-recognition
---

# SenseVoiceSmall-INT8-ONNX

> SenseVoiceSmall-INT8-ONNX - nocmtone 在 ModelScope 开源的模型。SenseVoiceSmall-INT8-ONNX

nocmtone/SenseVoiceSmall-INT8-ONNX 是 ModelScope 魔搭社区上的text-to-speech模型，采用 apache-2.0 许可，基于 iic/SenseVoiceSmall 构建。

- **Repository**: nocmtone/SenseVoiceSmall-INT8-ONNX
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Base model**: iic/SenseVoiceSmall
- **Tags**: asr, onnx, int8, sherpa-onnx, speech-recognition
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-09-17

Source: https://www.modelscope.cn/models/nocmtone/SenseVoiceSmall-INT8-ONNX

---

# SenseVoiceSmall-INT8-ONNX

sherpa-onnx distribution of
[SenseVoiceSmall](https://www.modelscope.cn/models/iic/SenseVoiceSmall) (int8),
used as a local, non-autoregressive speech recognizer.

## Why a repackaging exists at all

The official FunASR ONNX export
(`iic/SenseVoiceSmall-onnx`) **cannot be loaded by sherpa-onnx**, and not because
of the quantization — `model_quant.onnx` there is already int8. Two format
differences block it:

- the graph carries **no ONNX metadata**, and sherpa-onnx's SenseVoice loader
  requires at least `vocab_size` (loading fails with
  `'vocab_size' does not exist in the metadata`);
- it ships `tokens.json` (a JSON list), while sherpa-onnx reads a token table
  with one symbol per line.

This repository is the sherpa-onnx packaging of the same weights: identical model,
with the metadata sherpa-onnx expects and a `tokens.txt` in its format. `am.mvn`
is embedded in the graph, so only two files are needed.

## Files

| file | bytes | sha256 |
|---|---|---|
| `model.int8.onnx` | 239233841 | `c71f0ce00bec95b07744e116345e33d8cbbe08cef896382cf907bf4b51a2cd51` |
| `tokens.txt` | 315894 | `f449eb28dc567533d7fa59be34e2abca8784f771850c78a47fb731a31429a1dc` |

Total 228.5 MB — against 941 MB and 2293 MB for the two autoregressive tiers this
is intended to complement.

## Measured

On an i5-12600KF (16 logical cores, 6P+4E), decoding the same 11 × 6 s segments of
the same real English recording:

| engine | ms per 6 s segment | RTF |
|---|---|---|
| Qwen3-ASR 0.6B int8 (autoregressive) | 2744 | 0.46 |
| **SenseVoiceSmall int8 (this package)** | **226 @4 threads / 206 @8 threads** | **0.04** |

Roughly 12x, with an essentially identical transcript (996 vs 1002 characters over
the eleven segments). The cost is also flat in output length: being encoder-only +
CTC, it does not pay a per-token decode cost, which is what makes the
autoregressive tier slow on smaller machines.

## Languages

`auto`, `zh`, `yue`, `en`, `ja`, `ko` — five languages. This is **not** a
drop-in replacement for a multilingual tier; it is meant to sit alongside one.

## License

Apache License 2.0, as declared by the model's ModelScope page
([`iic/SenseVoiceSmall`](https://www.modelscope.cn/models/iic/SenseVoiceSmall)).

This repository only changes the packaging — the same weights in sherpa-onnx's
container format — not the licensing terms.