Starstruk Logo MarkStarstruk

v1.4.9

modelscope/FunASRv1.4.9Aug 30, 2026by github-actions[bot]

AI Summary

This release focuses on bug fixes for subtitle generation, auto-model timestamp handling, Paraformer padding, and realtime segment preservation. It also includes documentation updates for MOSS diarization and provides new prebuilt runtime binaries for various platforms, including support for Windows CUDA Blackwell.

Key Highlights

  • Fixed overlong source cues in subtitles to prevent display issues
  • Improved auto-model to preserve explicit timestamps and speaker text
  • Updated Paraformer to trim timestamp predictor padding per sample
  • Enhanced realtime functionality to preserve long segment tails
  • Added native SGLang path documentation for MOSS diarization

New Features

  • Fixed overlong source cues in subtitles
  • Preserved explicit timestamp and speaker text in auto-model
  • Trimmed timestamp predictor padding in Paraformer
  • Preserved long segment tails in realtime mode

Full Release Notes

## What's Changed
* fix(subtitles): split overlong source cues by @LauraGPT in https://github.com/modelscope/FunASR/pull/3574
* fix(auto-model): preserve explicit timestamp and speaker text by @John6666cat in https://github.com/modelscope/FunASR/pull/3553
* fix(paraformer): trim timestamp predictor padding per sample by @John6666cat in https://github.com/modelscope/FunASR/pull/3554
* fix(realtime): preserve long segment tails by @LauraGPT in https://github.com/modelscope/FunASR/pull/3576
* docs: add native SGLang path for MOSS diarization by @LauraGPT in https://github.com/modelscope/FunASR/pull/3577
* chore(release): prepare 1.4.9 by @LauraGPT in https://github.com/modelscope/FunASR/pull/3578

## New Contributors
* @John6666cat made their first contribution in https://github.com/modelscope/FunASR/pull/3553

**Full Changelog**: https://github.com/modelscope/FunASR/compare/v1.4.8...v1.4.9

<!-- 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/v1.4.9/funasr-llamacpp-linux-arm64.tar.gz) | `7bca29cfa3c9a08e235a62212ca9e00f6656e59a8f07078966a2bfda1e5aa1f9` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.9/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/v1.4.9/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `f02d41e98e9d4041f0896661007193810f025484d2175958f7c1313d5c90ec46` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.9/funasr-llamacpp-linux-x64.tar.gz) | `779967de1c528c2be966bcc47f246e7d3e6fcdb748d9491263062f4120f35e52` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.9/funasr-llamacpp-macos-arm64.tar.gz) | `bda59474202b887190f59d25b7b42c714469efae71276072c12fa0a38de68792` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.9/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/v1.4.9/funasr-llamacpp-windows-x64-cuda-blackwell.zip) | `e32961a753f40888182f352fa551159c5165a6a77718ae4ade316aedfea4b1c2` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.9/funasr-llamacpp-windows-x64-cuda.zip) | `148657911fb666b7af6ec43af2e23a0984e3259012b4c39f95631b717feb6840` |
| Windows x64 Vulkan | [funasr-llamacpp-windows-x64-vulkan.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.9/funasr-llamacpp-windows-x64-vulkan.zip) | `debf8007e55011cad06081e7b8a78972f1b8fe672bc324d41e650d68821f6a6a` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.9/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==1.4.9"
```
<!-- funasr-runtime-downloads:end -->