Inference Speed on Audio 120s (test)
479Inference Time (ms)LPA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LPAPulse Config=12/12, Precision=fp32, Backend=PyTorch/MPS, Hardware=Apple M4 Pro, Batch size=12026.03 | 479 | — | |
| LPAPulse Config=8/12, Precision=fp16, Backend=MLX, Hardware=Apple M4 Pro, Batch size=12026.03 | 540 | 3.27 | |
| LPAPulse Config=8/12, Precision=fp32, Backend=PyTorch/MPS, Hardware=Apple M4 Pro, Batch size=12026.03 | 895 | — | |
| Attention BaselinePrecision=fp32, Backend=PyTorch/MPS, Hardware=Apple M4 Pro, Batch size=12026.03 | 1,668 | — | |
| Attention BaselinePrecision=fp16, Backend=PyTorch/MPS, Hardware=Apple M4 Pro, Batch size=12026.03 | 1,767 | — |