v1.3.24

What's Changed

• feat(server): add --model-path and --hub options to funasr-server by @liudonghua123 in #3299
• fix: client lost the last segment of audio in online mode by @dio-del in #3301
• feat(runtime): add GGUF HTTP transcription wrapper by @LauraGPT in #3303
• feat(runtime): add Vulkan llama.cpp backend packaging by @LauraGPT in #3304
• docs(runtime): mention Vulkan asset in release notes by @LauraGPT in #3305
• docs: surface Vulkan llama.cpp runtime in README by @LauraGPT in #3306
• docs: clarify realtime partial and hotword behavior by @LauraGPT in #3308
• docs: require FunASR 1.3.23 for Nano guides by @LauraGPT in #3310
• docs: fix broken markdown links by @LauraGPT in #3311
• docs: add canonical Nano finetune Chinese guide path by @LauraGPT in #3312
• docs: refresh stale public FunASR links by @LauraGPT in #3313
• docs: refresh remaining stale FunASR links by @LauraGPT in #3314
• chore: refresh awesome MCP tracking status by @LauraGPT in #3315
• release: bump funasr to 1.3.24 by @LauraGPT in #3316

New Contributors

• @liudonghua123 made their first contribution in #3299
• @dio-del made their first contribution in #3301

Full Changelog: v1.3.23...v1.3.24

Runtime downloads

This Python release pairs with the current prebuilt llama.cpp / GGUF runtime release: runtime-llamacpp-v0.1.8.

Use these assets when you want the self-contained llama-funasr-* binaries instead of the Python package. The runtime release is shared by the current Python releases; v1.3.24 itself is the PyPI package release.

Platform	Asset	SHA-256
Linux arm64	funasr-llamacpp-linux-arm64.tar.gz	208752f36745700eaba91698f9d1e93df7b29d692b63a620483e7419480ece66
Linux x64 AVX2	funasr-llamacpp-linux-x64-avx2.tar.gz	a92f9910ac226985f3147ebbbaf3e65d6372b30914b2fd02674fcec2304d9074
Linux x64 Vulkan	funasr-llamacpp-linux-x64-vulkan.tar.gz	bc679446ee962b745cb4be30d10a14a60772349299d1756bfd09d4575b1c1827
Linux x64 portable	funasr-llamacpp-linux-x64.tar.gz	e10264253505250a16a369486623378a002d16034fa522163d01371e5657e955
macOS arm64	funasr-llamacpp-macos-arm64.tar.gz	cf2da7dbcaaff40d15179e1ec1981da6cff60305a229bb3e0f67039f2e5b6f01
Windows x64 AVX2	funasr-llamacpp-windows-x64-avx2.zip	717edaddc33d26cda60594262077a8573c52c96784fed9f4ee82cf8154a53935
Windows x64 CUDA	funasr-llamacpp-windows-x64-cuda.zip	b26fd7557032565af97d4fda9ca447db6b1af72925a6ba2ba7dbc01a1cfd05a7
Windows x64 portable	funasr-llamacpp-windows-x64.zip	e390fe2ca46c3554d0ea04832f5804f82a8c427c815eb9e7c7e9954d7cc5866b

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:

python -m pip install -U "funasr==1.3.24"