snac-sweep
| Crates.io | snac-sweep |
| lib.rs | snac-sweep |
| version | 0.1.3 |
| created_at | 2025-10-17 08:25:58.155963+00 |
| updated_at | 2025-10-17 08:59:49.14353+00 |
| description | Sweep batch size, chunk size, and session count to benchmark ONNX decoder latency and RTF. |
| homepage | |
| repository | |
| max_upload_size | |
| id | 1887281 |
| size | 78,021 |
Ryan Li (ryanli)
documentation
README
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