Fact · Speech recognition
16times faster than real time
In our October 2026 benchmark on a Mac with an M2 Pro, Whisper large-v3-turbo transcribed 100 Portuguese FLEURS recordings about 16 times faster than real time.
Measured by us on October 19, 2026, from 100 recordings
Our own measurement
This number comes from our benchmark, not from another publication. The full record (the setup, every recording's checksum, every transcript and timing) is published, so you can recompute it.
- What it measures
- OpenAI Whisper large-v3-turbo, 5-bit quantized (ggml-large-v3-turbo-q5_0.bin), run through whisper.cpp 1.9.4 with Metal on the GPU, with the language given. Run on macOS 26.6.2, 16 GB of memory; other apps were open, as on any working Mac.
- How it is measured
- Speed = 1,284.5 seconds of audio / 79.58 seconds of processing = 16.1 times real time, over 100 recordings processed one at a time on a warm engine.
- What it does not show
- Speed depends on the chip, memory and what else the Mac is doing, and short sentences carry a fixed overhead per recording, so long recordings run faster than this.
In the data
A row of Speech Recognition Speed: Real-Time Factor Data, as Whisper large-v3-turbo, Portuguese (M2 Pro): 16 times faster than real time.
- System
- Whisper large-v3-turbo
- Kind
- Open model
- Hardware
- Apple M2 Pro
- Test set
- FLEURS
- Year
- 2026