v1.4.3

modelscope/FunASRv1.4.3Aug 21, 2026by LauraGPT

AI Summary

FunASR 1.4.3 introduces an optional Silero VAD adapter with configurable thresholds and ONNX support, alongside optimizations for speaker embedding clustering. The release refreshes ecosystem integrations and includes verified prebuilt llama.cpp runtimes for Linux, macOS, and Windows.

Key Highlights

Adds an optional Silero VAD adapter compatible with `AutoModel(vad_model="silero-vad")`
Optimizes speaker embedding clustering using normalized fixed-K clustering for large sets
Refreshes ecosystem with validated MLX Audio and OpenMAIC FunASR integrations
Includes verified `runtime-llamacpp-v0.2.0` builds for nine platforms (Linux, macOS, Windows)

New Features

Silero VAD adapter with configurable thresholds and 8/16 kHz input support
ONNX mode for the Silero VAD adapter
Normalized fixed-K clustering for speaker embeddings
MLX Audio integration
OpenMAIC FunASR integration

Full Release Notes

## FunASR 1.4.3

Install or upgrade the Python package:

```bash
python -m pip install -U "funasr==1.4.3"
```

Enable the optional Silero VAD adapter:

```bash
python -m pip install -U "funasr[silero]==1.4.3"
```

PyPI: https://pypi.org/project/funasr/1.4.3/

### Python package

- Adds an optional Silero VAD adapter for `AutoModel(vad_model="silero-vad")`, with FunASR-compatible millisecond segments, configurable thresholds, 8/16 kHz input, ONNX mode, and bounded segment lengths.
- Routes large speaker-embedding sets with a known speaker count through normalized fixed-K clustering instead of memory-heavy dense spectral clustering.

### Ecosystem and deployment

- Refreshes the source release with validated MLX Audio and OpenMAIC FunASR integrations.
- Updates product-site discovery, deployment routing, and current llama.cpp runtime contracts.

### Prebuilt llama.cpp runtime

The release includes verified `runtime-llamacpp-v0.2.0` builds for nine Linux, macOS, and Windows targets, including Windows CUDA and Linux/Windows Vulkan. Use `SHA256SUMS-v1.4.3` to verify every Python and runtime artifact after download.

**Full Changelog:** https://github.com/modelscope/FunASR/compare/v1.4.2...v1.4.3

<!-- funasr-runtime-downloads:start -->
## Runtime downloads

This Python release pairs with the current prebuilt llama.cpp / GGUF runtime release: [runtime-llamacpp-v0.2.0](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.0).

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/v1.4.3/funasr-llamacpp-linux-arm64.tar.gz) | `c78987b2384c6aef339aea1bcd0e130070455d6394fa7ab7ca26840ead10d5da` |
| Linux x64 AVX2 | [funasr-llamacpp-linux-x64-avx2.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-linux-x64-avx2.tar.gz) | `02e10e9a46ea76a040c45d431efe51a3324e64f08c24d38e18c8a4d2781490cd` |
| Linux x64 Vulkan | [funasr-llamacpp-linux-x64-vulkan.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-linux-x64-vulkan.tar.gz) | `caf71b8c0b4c3249cebc4175e5406d3c588eb9e8966a00d571d4cc5070405385` |
| Linux x64 portable | [funasr-llamacpp-linux-x64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-linux-x64.tar.gz) | `15e6407143b4fb91d90bb37f2a41c64c4d48ea0fbe6404b88a9b70269c84f240` |
| macOS arm64 | [funasr-llamacpp-macos-arm64.tar.gz](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-macos-arm64.tar.gz) | `416cbb289e31cb7575365d382155074e922fd061807a37b9ca0247dabd9bc6f9` |
| Windows x64 AVX2 | [funasr-llamacpp-windows-x64-avx2.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-windows-x64-avx2.zip) | `4db0f11f603c324a63545cd7009cdd45bb45576efe282cec22796b5fd42d8ea1` |
| Windows x64 CUDA | [funasr-llamacpp-windows-x64-cuda.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-windows-x64-cuda.zip) | `7f2f9ef4d7e0291b284a295ec74bbeca9ea635a7f5f42d0ad06eb780c0d6efc1` |
| Windows x64 Vulkan | [funasr-llamacpp-windows-x64-vulkan.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-windows-x64-vulkan.zip) | `90b45240c6ccc9177c25490a11848de60a406e129391c8736b14521c0c28cdcb` |
| Windows x64 portable | [funasr-llamacpp-windows-x64.zip](https://github.com/modelscope/FunASR/releases/download/v1.4.3/funasr-llamacpp-windows-x64.zip) | `297c962346d7e30d7a7c2c860dfaab3ff07d01fddf15e6fc5212ca9545441a51` |

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==1.4.3"
```
<!-- funasr-runtime-downloads:end -->