v6.2.2
Project-HAMi/HAMiv6.2.2Sep 17, 2026by adamnsandle
Upgrading?
AI Summary
Adds an offline ONNX sequence model for silero-vad, currently optimized for 16 kHz sampling rates.
Key Highlights
- Added offline ONNX sequence support
- Separate `silero_vad_16k_sequence.onnx` model file
- New Python API for loading and using the sequence model
New Features
- Offline ONNX sequence support
- 16 kHz audio support
- Separate sequence model file
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
ollama/ollama★ 184,207
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,051
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,612
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.
junegunn/fzf★ 83,716
:cherry_blossom: A command-line fuzzy finder