SenseVoice Releases

Prebuilt self-contained binaries for the FunASR llama.cpp runtime v0.2.1, supporting SenseVoice, Fun-ASR-Nano, and Paraformer with built-in FSMN-VAD. This release improves GPU selection logic to prefer discrete GPUs over integrated ones and updates Vulkan support.

Aug 27, 2026

Prebuilt binaries for the llama.cpp runtime with SenseVoice, Paraformer, and Fun-ASR-Nano support. This update moves the SenseVoice source snapshot to the current main branch and includes a security fix for the YAML loader.

Jul 24, 2026

Prebuilt self-contained binaries for the FunASR llama.cpp runtime with added explicit AVX2 assets for better performance. This release addresses SIGILL issues and provides optimized options for high-performance CPUs.

Jun 29, 2026

A portable rebuild of the llama.cpp runtime binaries with conservative CPU flags to prevent crashes caused by instruction set mismatches. This version disables high-ISA flags to ensure compatibility across different hardware.

Jun 28, 2026

First prebuilt, self-contained binaries for running SenseVoice locally without Python or build steps, featuring built-in FSMN-VAD. This release introduces support for q8 GGUF models to reduce size without sacrificing accuracy.

Jun 21, 2026

Prebuilt, self-contained binaries for running SenseVoice locally without Python, torch, or local compilation. This release emphasizes zero-dependency operation and provides performance benchmarks against whisper.cpp.

Jun 21, 2026

The first official release of the SenseVoiceSmall checkpoint, offering multilingual speech understanding capabilities. This release includes support for ASR, language identification, emotion recognition, and audio event detection.

May 25, 2026