GOESB

GOESB — Global Open Edge Speech Benchmark · pronounced “goose-bee”

Leaderboard

Objective, reproducible benchmarks for local (edge) speech AI. Every result here re-verified its hash and signature before being accepted — see why you can trust the numbers. New here? Read the docs.

This is every verified result, filterable and sortable. Looking for a single best recommendation for your constraints instead? Try the homepage →

Lowest energyFastest (lowest RTF)Most accurate (lowest WER)
Clear
Quality gates:WER < 5%WER < 10%WER < 15%
custom…
wer ≤ 0.10

Sorted by most recently submitted · 4 results · click a metric below to sort by it

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
whisper-large-v3-nl-batchfaster-whisper / whisper-large-v3apple-m1-profleurs-nl
cer: 0.0100 ratiower: 0.0438 ratioram_mb: 3685.48 MBcpu_pct: 430.35 %real_time_factor: 0.6461 ratio
2026-07-28T21:35:20Z
details
Profile
whisper-large-v3-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
beam_size
5
quantization
int8
threads
4
vad
true
whisper-medium-nl-batchfaster-whisper / whisper-mediumapple-m1-profleurs-nl
cer: 0.0156 ratiower: 0.0474 ratioram_mb: 2021.80 MBcpu_pct: 431.53 %real_time_factor: 0.3789 ratio
2026-07-28T21:36:57Z
details
Profile
whisper-medium-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
beam_size
5
quantization
int8
threads
4
vad
true
whispercpp-large-v3-nl-batchwhisper-cpp / whisper-large-v3apple-m1-profleurs-nl
cer: 0.0095 ratiower: 0.0401 ratioram_mb: 3559.60 MBcpu_pct: 338.20 %real_time_factor: 0.5255 ratio
2026-07-28T21:41:12Z
details
Profile
whispercpp-large-v3-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
threads
4
whispercpp-medium-nl-batchwhisper-cpp / whisper-mediumapple-m1-profleurs-nl
cer: 0.0228 ratiower: 0.0620 ratioram_mb: 1906.52 MBcpu_pct: 340.14 %real_time_factor: 0.2974 ratio
2026-07-28T21:42:27Z
details
Profile
whispercpp-medium-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
threads
4

Constant across this view: beam_size 5 · quantization int8 · threads 4 · vad true

* profile default