whisper.cpp v1.8.0
whisper.cpp v1.8.0 releases with flash attention enabled by default, delivering encoder and decoder performance gains across M1 Pro and M2 Ultra hardware.
Overview Flash attention is now enabled by default Performance improvements M1 Pro | CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | M1 Pro | METAL | tiny | 1 | 0 | 32.44 | 1.71 | 0.43 | 0.04 | 8a67c55c | | M1 Pro | METAL | base | 1 | 0 | 63.54 | 2.62 | 0.71 | 0.06 | 8a67c55c | | M1 Pro | METAL | small | 1 | 0 | 200.30 | 5.34 | 1.72 | 0.17 | 8a67c55c | | M1 Pro | METAL | medium | 1 | 0 | 580.06 | 11.71 | 4.18 | 0.45 | 8a67c55c | | CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | M1 Pro | METAL | tiny | 1 | 1 | 22.09 | 1.84 | 0.43 | 0.03 | 8a67c55c | | M1 Pro | METAL | base | 1 | 1 | 40.57 | 2.22 | 0.44 | 0.04 | 8a67c55c | | M1 Pro | METAL | small | 1 | 1 | 135.15 | 4.23 | 0.95 | 0.12 | 8a67c55c | | M1 Pro | METAL | medium | 1 | 1 | 395.18 | 9.14 | 2.21 | 0.30 | 8a67c55c | M2 Ultra | CPU | Config | Model | Th | FA | Enc.
| Dec. | Bch5 | PP | Commit | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | M2 ULTRA | METAL | tiny | 1 | 0 | 8.63 | 1.09 | 0.27 | 0.01 | b57b9d3a | | M2 ULTRA | METAL | tiny-q5_0 |…
- github.comwhisper.cpp v1.8.0primary