FunASR llama.cpp runtime runtime-llamacpp-v0.1.4

Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime.

This release keeps the default x64 assets conservative for maximum CPU compatibility and adds explicit x64-avx2 assets for CPUs with AVX2/FMA/F16C/BMI2. If v0.1.3 fixed SIGILL but was too slow on your machine, try funasr-llamacpp-windows-x64-avx2.zip.

Use the default x64 package if the AVX2 package fails with Illegal instruction / SIGILL.

FunASR llama.cpp runtime v0.1.3

Portable rebuild of the FunASR llama.cpp / GGUF runtime binaries.

This release rebuilds the v0.1.2 runtime with conservative CPU flags for the generic x64 assets. In particular, it disables ggml native CPU tuning and high-ISA AVX/AVX2/AVX512/VNNI/FMA/F16C/BMI2 flags so the prebuilt binaries do not depend on the GitHub Actions runner CPU instruction set.

Use this version if v0.1.2 crashes with Illegal instruction, SIGILL, or Windows error 0xC000001D.

FunASR llama.cpp runtime v0.1.2

Prebuilt self-contained binaries for running SenseVoice (and Paraformer / Fun-ASR-Nano) locally with the FunASR llama.cpp / GGUF runtime — built-in FSMN-VAD, whisper.cpp-style on-device ASR, strong on Chinese & Cantonese.

New: q8 GGUF models are ~half the size of f16 with the same accuracy.

bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/sensevoice-small-q8.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav

No Python, no build. Linux (x64/arm64), macOS (arm64), Windows (x64). Docs: runtime/llama.cpp/README.md.

FunASR llama.cpp runtime v0.1.1

Prebuilt, self-contained binaries to run SenseVoice (and Paraformer / Fun-ASR-Nano) locally with the FunASR llama.cpp / GGUF runtime — built-in FSMN-VAD, whisper.cpp-style on-device ASR, strong on Chinese & Cantonese.

bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/SenseVoiceSmall-f16.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav

No Python, no build, no torch. Binaries for Linux (x64/arm64), macOS (arm64), Windows (x64). Docs: runtime/llama.cpp/README.md. CER (micro-avg): SenseVoice 8.01% vs whisper.cpp small 22%.

v1.0.0: SenseVoice — Multilingual Speech Understanding

SenseVoice v1.0.0

The first official release of SenseVoice, a speech foundation model for multilingual speech understanding.

Highlights

• Multilingual ASR — 50+ languages, superior to Whisper on Chinese and Cantonese
• Speech Emotion Recognition — Happy, Sad, Angry, Neutral detection
• Audio Event Detection — Background music, applause, laughter, crying, coughing
• Ultra-fast inference — Non-autoregressive, 70ms for 10 seconds of audio (15x faster than Whisper)
• Speaker Diarization — Works with FunASR's VAD + SPK pipeline for who-said-what

Quick Start

from funasr import AutoModel

model = AutoModel(model="iic/SenseVoiceSmall", device="cuda")
result = model.generate(input="audio.wav")
print(result[0]["text"])

Models

Model	Languages	Parameters	Download
SenseVoice-Small	5 (zh/en/ja/ko/yue)	234M	ModelScope · HuggingFace

Links

• Paper: FunAudioLLM
• Demo: ModelScope · HuggingFace
• Toolkit: github.com/modelscope/FunASR
• Website: www.funasr.com