v6.2.2
Gen-Verse/MMaDAv6.2.2Sep 17, 2026by adamnsandle
Upgrading?
AI Summary
This release introduces offline ONNX sequence support for the Silero VAD model, optimized for 16 kHz audio processing.
Key Highlights
- Added offline ONNX sequence capability with a dedicated 16 kHz model file.
- Introduced a new loading method using `load_silero_vad(sequence=True)`.
- Separate model file `silero_vad_16k_sequence.onnx` is now available.
New Features
- Support for offline ONNX sequence processing in speech detection.
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★ 491,175
A collective list of free APIs
NousResearch/hermes-agent★ 256,017
The agent that grows with you
yt-dlp/yt-dlp★ 200,192
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,525
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,703
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.