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)
AnyEvery verified result, batch and streaming mixed together.
AnyBatchStreamingConcurrency

Sorted by most recently submitted · 5 results · click a metric below to sort by it

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
whisper-tiny-pt-batchfaster-whisper / whisper-tinycudanvidia-rtx-a4000fleurs-pt
cer: 0.0300 ratiower: 0.1202 ratioram_mb: 747.90 MBcpu_pct: 652.77 %temperature_c: 75 °Creal_time_factor: 0.0155 ratio
2026-07-31T07:38:44Z
details
Profile
whisper-tiny-pt-batch@1.1.0
Pack
fleurs-pt@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-large-v3-nl-batchfaster-whisper / whisper-large-v3cudanvidia-rtx-a4000fleurs-nl
cer: 0.0095 ratiower: 0.0401 ratioram_mb: 4241.03 MBcpu_pct: 262.22 %temperature_c: 65 °Creal_time_factor: 0.0674 ratio
2026-07-30T22:16:54Z
details
Profile
whisper-large-v3-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-medium-nl-batchfaster-whisper / whisper-mediumcudanvidia-rtx-a4000fleurs-nl
cer: 0.0173 ratiower: 0.0474 ratioram_mb: 2618.65 MBcpu_pct: 295.85 %temperature_c: 71 °Creal_time_factor: 0.0518 ratio
2026-07-30T22:17:24Z
details
Profile
whisper-medium-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-large-v3-nl-batchfaster-whisper / whisper-large-v3cudaintel-core-i7-1370pfleurs-nl
cer: 0.0095 ratiower: 0.0401 ratioram_mb: 3460.44 MBcpu_pct: 168.21 %real_time_factor: 0.5050 ratio
2026-07-30T07:35:39Z
details
Profile
whisper-large-v3-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-medium-nl-batchfaster-whisper / whisper-mediumcudaintel-core-i7-1370pfleurs-nl
cer: 0.0167 ratiower: 0.0511 ratioram_mb: 1947.26 MBcpu_pct: 195.61 %real_time_factor: 0.3296 ratio
2026-07-30T07:37:33Z
details
Profile
whisper-medium-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true

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

* profile default

76–80 of 80
← PrevPage 4 of 4Next →