v1.3.2

ByteDance-Seed/SeedVRv1.3.2May 23, 2026by LauraGPT

AI Summary

v1.3.2 addresses a critical bug regarding HuggingFace Hub parameter propagation to sub-models and introduces a comprehensive performance benchmark page.

Key Highlights

Fixed `hub="hf"` parameter propagation to VAD/PUNC/SPK sub-models
Fixed Qwen3-ASR ImportError masking
Added comprehensive benchmark page with speed metrics
Benchmark results show high realtime speeds (e.g., SenseVoice-Small at 170x)

New Features

Performance benchmark page (https://modelscope.github.io/FunASR/benchmark.html)

Full Release Notes

## What's New

### Bug Fix
- **Fixed hub parameter propagation** — When using `hub="hf"`, the parameter is now correctly forwarded to VAD/PUNC/SPK sub-models. Previously, users on HuggingFace would get 404 errors for sub-models. (#2859)

### Improvements
- Updated PyPI metadata with better description, keywords, and project URLs
- Added comprehensive benchmark page: https://modelscope.github.io/FunASR/benchmark.html

### Benchmark Results (PyTorch, GPU)

| Model | Type | Speed |
|-------|------|-------|
| SenseVoice-Small | NAR | **170x** realtime |
| Paraformer-Large | NAR | **120x** realtime |
| Whisper-large-v3-turbo | AR | 46x realtime |
| Fun-ASR-Nano | LLM | 17x realtime |
| Whisper-large-v3 | AR | 13.4x realtime |

### Install / Upgrade
```bash
pip install --upgrade funasr
```

### Quick Start
```python
from funasr import AutoModel
model = AutoModel(model="FunAudioLLM/SenseVoiceSmall", hub="hf", vad_model="funasr/fsmn-vad", device="cuda")
result = model.generate(input="audio.wav")
```