v6.2.2
agentscope-ai/QwenPawv6.2.2Sep 17, 2026by adamnsandle
Upgrading?
AI Summary
Adds an offline ONNX sequence model for Silero VAD, specifically supporting 16kHz audio sampling rates, with a new separate model file and updated Python API.
Key Highlights
- Added offline ONNX sequence model
- Separate `silero_vad_16k_sequence.onnx` model file
- New Python API `get_speech_timestamps_sequence`
New Features
- Offline ONNX sequence model support
- 16kHz audio sampling support
Full Release Notes
Added offline ONNX sequence to release GIL- #795
- 16 kHz only for now
- separate `silero_vad_16k_sequence.onnx` model
```python3
from silero_vad import load_silero_vad, get_speech_timestamps_sequence, read_audio
model = load_silero_vad(sequence=True) # loads silero_vad_16k_sequence.onnx
audio = read_audio("audio.wav", sampling_rate=16000)
ts = get_speech_timestamps_sequence(audio, model, return_seconds=True)
```Related Repositories
public-apis/public-apis★ 491,211
A collective list of free APIs
NousResearch/hermes-agent★ 256,078
The agent that grows with you
yt-dlp/yt-dlp★ 200,249
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,556
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,699
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.