v1.4.12

modelscope/FunASRv1.4.12Sep 1, 2026by github-actions[bot]

AI Summary

FunASR v1.4.12 focuses on stabilizing runtime performance and expanding deployment options. Key updates include fixes for real-time partials and vLLM decoding, alongside the addition of new runtime binaries for various platforms.

Key Highlights

Stabilized fp16 vLLM decoding for the fun-asr-nano model
New feature to serve MOSS diarization across the deployment stack
Fix to preserve aligned long-segment partials in real-time mode
Release of cross-platform runtime binaries (llama.cpp) for Linux, macOS, and Windows

New Features

Serve MOSS diarization across the deployment stack

Full Release Notes

## What's Changed
* fix(realtime): preserve aligned long-segment partials by @LauraGPT in https://github.com/modelscope/FunASR/pull/3589
* docs: keep README updates focused by @LauraGPT in https://github.com/modelscope/FunASR/pull/3594
* feat: serve MOSS diarization across deployment stack by @LauraGPT in https://github.com/modelscope/FunASR/pull/3599
* fix(fun-asr-nano): stabilize fp16 vLLM decoding by @LauraGPT in https://github.com/modelscope/FunASR/pull/3597
* release: prepare FunASR 1.4.12 by @LauraGPT in https://github.com/modelscope/FunASR/pull/3602


**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.4.11...v1.4.12

<!-- funasr-runtime-downloads:start -->
## Runtime downloads

This Python release pairs with the current prebuilt llama.cpp / GGUF runtime release: [runtime-llamacpp-v0.2.6](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.6).

The same verified runtime assets are attached directly to this Python release so users can find the package and self-contained `llama-funasr-*` binaries in one place.

| Platform | Asset | SHA-256 |
|---|---|---|
| Linux arm64 | [funasr-llamacpp-linux-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-linux-arm64.tar.gz) | `7bca29cfa3c9a08e235a62212ca9e00f6656e59a8f07078966a2bfda1e5aa1f9` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-linux-x64-avx2.tar.gz) | `aaebc5470f846ce915200b35d6e9f9bd0a0d3ed399d39e49bdeb7a1f1782bc70` |
| Linux x64 Vulkan | [funasr-llamacpp-linux-x64-vulkan.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `f02d41e98e9d4041f0896661007193810f025484d2175958f7c1313d5c90ec46` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-linux-x64.tar.gz) | `779967de1c528c2be966bcc47f246e7d3e6fcdb748d9491263062f4120f35e52` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-macos-arm64.tar.gz) | `bda59474202b887190f59d25b7b42c714469efae71276072c12fa0a38de68792` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-windows-x64-avx2.zip) | `062cda8fefadd31c3e811227116daccf448a8520f4b0bb168d225c896e65ebbd` |
| Windows x64 CUDA Blackwell (sm_120) | [funasr-llamacpp-windows-x64-cuda-blackwell.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-windows-x64-cuda-blackwell.zip) | `e32961a753f40888182f352fa551159c5165a6a77718ae4ade316aedfea4b1c2` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-windows-x64-cuda.zip) | `148657911fb666b7af6ec43af2e23a0984e3259012b4c39f95631b717feb6840` |
| Windows x64 Vulkan | [funasr-llamacpp-windows-x64-vulkan.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-windows-x64-vulkan.zip) | `debf8007e55011cad06081e7b8a78972f1b8fe672bc324d41e650d68821f6a6a` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.12/funasr-llamacpp-windows-x64.zip) | `f6a73a548413ba9fbaf2145263ea66ec53cbdad1fb11790dbeeee493e339492e` |

Quick start: download one asset, unpack it, then run the bundled `download-funasr-model.sh <sensevoice|paraformer|nano>` helper and one of `llama-funasr-cli`, `llama-funasr-sensevoice`, or `llama-funasr-paraformer`.

For Python users, install from PyPI:

```bash
python -m pip install -U "funasr==1.4.12"
```
<!-- funasr-runtime-downloads:end -->
## Verify downloads

All release assets are listed in [SHA256SUMS](https://github.com/modelscope/FunASR/releases/download/v1.4.12/SHA256SUMS). Run sha256sum -c SHA256SUMS after downloading the files you need.