Speaker diarization on a MacBook Air M3: 4.4x faster on the GPU, 2.5x for the whole pipeline
DEV Community
Speaker diarization on a MacBook Air M3: 4.4x faster on the GPU, 2.5x for the whole pipeline
Moving pyannote.audio diarization from CPU to Apple's GPU (MPS) made that stage 4.4x faster and the whole local transcription pipeline 2.5x faster. Numbers, code and what I did not measure.
0 comments
No comments yet.