mirror of
https://github.com/hanzoai/ml.git
synced 2026-11-20 23:08:29 +00:00
Three-way per file through the rename: base 39355c6c91, theirs the upstream
merge of main with 35d7ae7c (via 7ef6a694d), ours origin/main.
Lands the barrier thread pool, runtime CPU feature dispatch, aarch64 and x86
repacked quantized kernels (indexed_gemv, gemv_fused_shared_lhs), quantized
embedding on CPU/Metal/CUDA, paged flash-attn kernels, cutile fused MoE, the
in-place op aliasing API, parking_lot storage locks, Metal buffer builders and
debug labels, safetensors 0.8, hf-hub 1.0, tokenizers 0.23.
Ours keeps ROCm, Vulkan, wgpu, the IQ/MXFP4/NVFP4/TQ dtypes, and the i-quant
weight/activation block split in matmul. Our backends ride InplaceOpN and the
quantized embedding; Metal get_rows gains the IQ kernels. ug leaves, as upstream.
Co-authored-by: Hanzo Dev <[email protected]>
silero-vad: Voice Activity Detection
Silero VAD (v5) detects voice activity in streaming audio.
This example uses the models available in the hugging face onnx-community/silero-vad.
Running the example
using arecord
$ arecord -t raw -f S16_LE -r 16000 -c 1 -d 5 - | cargo run --example silero-vad --release --features onnx -- --sample-rate 16000
using SoX
$ rec -t raw -r 48000 -b 16 -c 1 -e signed-integer - trim 0 5 | sox -t raw -r 48000 -b 16 -c 1 -e signed-integer - -t raw -r 16000 -b 16 -c 1 -e signed-integer - | cargo run --example silero-vad --release --features onnx -- --sample-rate 16000