v1.4.10

modelscope/FunASRv1.4.10Aug 30, 2026by github-actions[bot]

AI Summary

This release improves subtitle segmentation for long Chinese sentences by balancing duration and length while preferring lexical boundaries and punctuation. It also includes verified llama.cpp runtime archives for multiple platforms and hardware backends.

Key Highlights

Improved subtitle segmentation logic prefers Jieba lexical boundaries and punctuation over mechanical filling to 42 characters.
Includes verified llama.cpp runtime archives for Linux, macOS, and Windows (CPU, Vulkan, CUDA, Blackwell).
Test sample demonstrates zero duration or length violations (10m33s sample converted 84 segments to 133 cues).
Preserves natural phrases such as '钟书成为' and '扭了一下'.

New Features

Verified llama.cpp runtime archives for various platforms and hardware backends.

Full Release Notes

## FunASR 1.4.10

This release fixes readable subtitle fallback boundaries for overlong Chinese sentences. Instead of mechanically filling each cue to the 42-character limit, FunASR now balances duration and length while preferring Jieba lexical boundaries, punctuation, script transitions, and real timestamp gaps.

On the reporter exact 10m33s mixed Chinese/Korean sample, 84 source segments became 133 cues with:
- maximum duration: 7,860 ms
- maximum length: 42 characters
- zero duration or length violations
- phrases such as 钟书成为 and 扭了一下 preserved

Issue #3539 remains open pending reporter confirmation on the published package.

## Install

python -m pip install -U "funasr==1.4.10"

## Python package SHA-256

b520f5f91e1f7ae86fd6f8fffb0980f7a9753ad34d2a13d8a9846caa60bcda19  funasr-1.4.10-py3-none-any.whl
67dd08ba621459157de7609ed481d5341bb8b26c23b1f745cc31bef33cf61ae4  funasr-1.4.10.tar.gz

The release also includes the verified llama.cpp runtime archives for Linux, macOS, and Windows, including CPU, Vulkan, CUDA, and Blackwell variants where supported.

Fix: #3583
Build workflow: https://github.com/modelscope/FunASR/actions/runs/33333569782