v1.4.8

modelscope/FunASRv1.4.8Aug 30, 2026by github-actions[bot]

AI Summary

This release expands Moss model capabilities by adding support for vLLM diarized responses and long transcriptions. It also introduces Windows CUDA assets targeting the Blackwell architecture (sm_120) and fixes a download snapshot error.

Key Highlights

Support for vLLM diarized responses and long transcriptions in Moss.
Release of Windows CUDA Blackwell runtime assets for RTX 50 series GPUs.
Fix for download snapshot error preservation.
Updated documentation for runtime downloads and official recipes.

New Features

Moss vLLM diarized responses support.
Moss long vLLM transcriptions support.
Windows CUDA Blackwell runtime assets.

Full Release Notes

## What's Changed
* fix(download): preserve snapshot errors by @LauraGPT in https://github.com/modelscope/FunASR/pull/3565
* feat(moss): support vLLM diarized responses by @LauraGPT in https://github.com/modelscope/FunASR/pull/3566
* docs: refresh repository roadmap and issue boundaries by @LauraGPT in https://github.com/modelscope/FunASR/pull/3567
* feat(moss): support long vLLM transcriptions by @LauraGPT in https://github.com/modelscope/FunASR/pull/3568
* docs: expose MOSS LocalAI edge path by @LauraGPT in https://github.com/modelscope/FunASR/pull/3569
* feat(runtime): publish Windows CUDA asset for Blackwell by @LauraGPT in https://github.com/modelscope/FunASR/pull/3570
* docs(runtime): publish v0.2.6 download matrix by @LauraGPT in https://github.com/modelscope/FunASR/pull/3571
* docs(site): sync v0.2.6 and official MOSS recipe by @LauraGPT in https://github.com/modelscope/FunASR/pull/3572
* chore(release): prepare 1.4.8 by @LauraGPT in https://github.com/modelscope/FunASR/pull/3573


**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.4.7...v1.4.8

<!-- 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/v1.4.8/funasr-llamacpp-linux-arm64.tar.gz) | `7bca29cfa3c9a08e235a62212ca9e00f6656e59a8f07078966a2bfda1e5aa1f9` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.8/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/v1.4.8/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `f02d41e98e9d4041f0896661007193810f025484d2175958f7c1313d5c90ec46` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.8/funasr-llamacpp-linux-x64.tar.gz) | `779967de1c528c2be966bcc47f246e7d3e6fcdb748d9491263062f4120f35e52` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.8/funasr-llamacpp-macos-arm64.tar.gz) | `bda59474202b887190f59d25b7b42c714469efae71276072c12fa0a38de68792` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.8/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/v1.4.8/funasr-llamacpp-windows-x64-cuda-blackwell.zip) | `e32961a753f40888182f352fa551159c5165a6a77718ae4ade316aedfea4b1c2` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.8/funasr-llamacpp-windows-x64-cuda.zip) | `148657911fb666b7af6ec43af2e23a0984e3259012b4c39f95631b717feb6840` |
| Windows x64 Vulkan | [funasr-llamacpp-windows-x64-vulkan.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.8/funasr-llamacpp-windows-x64-vulkan.zip) | `debf8007e55011cad06081e7b8a78972f1b8fe672bc324d41e650d68821f6a6a` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.8/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==1.4.8"
```
<!-- funasr-runtime-downloads:end -->