v1.4.1

modelscope/FunASRv1.4.1Aug 4, 2026by LauraGPT

AI Summary

This release introduces LoRA fine-tuning support for the Qwen3 LLM, fixes the Hugging Face paraformer-en alias routing, and enhances output capabilities by adding JSONL transcript/timestamp support to ONNX binaries.

Key Highlights

Adds LoRA fine-tuning support for Qwen3 LLM inside Fun-ASR-Nano
Routes HF paraformer-en alias to official English checkpoint
Adds stable JSONL transcript and timestamp output to ONNX binaries
Adds reproducible SenseVoice TensorRT/Triton deployment path
Adds openclaw-funasr realtime transcription provider

New Features

LoRA fine-tuning for Qwen3 LLM
JSONL transcript output for native ONNX Runtime
OpenClaw Talk and Voice Call provider
HF alias routing correction
Reproducible SenseVoice deployment

Full Release Notes

## FunASR 1.4.1

Install or upgrade the Python package:

```bash
pip install -U funasr==1.4.1
```

### Python package

- Routes the Hugging Face `paraformer-en` alias to the official English checkpoint instead of silently downloading the Chinese model.
- Adds LoRA fine-tuning support for the Qwen3 LLM inside Fun-ASR-Nano, including deterministic regression coverage and bilingual guidance.
- Avoids checkpoint-selection failures when a save step has not yet produced validation metrics.

### Tagged source

- Adds stable JSONL transcript and timestamp output to the native ONNX Runtime offline and two-pass binaries.
- Adds a reproducible SenseVoice TensorRT/Triton deployment path.
- Adds the `openclaw-funasr` realtime transcription provider for OpenClaw Talk and Voice Call.
- Includes native runtime buffer-ownership fixes merged after `v1.4.0`.

### Prebuilt llama.cpp runtime

The release includes the same verified FunASR llama.cpp / GGUF runtime builds for nine Linux, macOS, and Windows targets. Use `SHA256SUMS-v1.4.1` to verify every Python and runtime artifact after download.

**Full Changelog:** https://github.com/modelscope/FunASR/compare/v1.4.0...v1.4.1