4 releases
Uses new Rust 2024
| 0.1.3 | Oct 17, 2025 |
|---|---|
| 0.1.2 | Oct 17, 2025 |
| 0.1.1 | Oct 17, 2025 |
| 0.1.0 | Oct 17, 2025 |
#586 in Machine learning
22KB
218 lines
snac-sweep
Benchmark sweep for SNAC's ONNX decoder inference: varies sessions (parallel sessions), chunk size (sequence length without context), and batch size to find the largest throughput (sessions × batch) under real-time factor (RTF) < 1.
Install
cargo install snac-sweep
Usage
snac-sweep --context-size <N> --max-chunk-size <M> --model <onnx-file>
- context-size (default
3): number of context windows added to sequence length. - max-chunk-size (default
3): max chunk size to sweep (seq_len from 1..=M). - model (default
decoder_model_fp16.onnx): model file under https://huggingface.co/onnx-community/snac_24khz-ONNX/tree/main/onnx.
RTF calculation is based on 24kHz sample rate (each chunk is 2048 samples).
Example
snac-sweep --context-size 3 --max-chunk-size 5 --model decoder_model_fp16.onnx
Dependencies
~14–21MB
~284K SLoC