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 · 15 results · click a metric below to sort by it

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
whisper-medium-fr-batchfaster-whisper / whisper-mediumcudanvidia-rtx-4090fleurs-fr
cer: 0.0357 ratiower: 0.0909 ratioram_mb: 1924.62 MBcpu_pct: 588.33 %temperature_c: 47 °Creal_time_factor: 0.0494 ratio
2026-07-31T08:36:25Z
details
Profile
whisper-medium-fr-batch@1.1.0
Pack
fleurs-fr@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-medium-nl-batchfaster-whisper / whisper-mediumcudanvidia-rtx-4090fleurs-nl
cer: 0.0173 ratiower: 0.0584 ratioram_mb: 1937.79 MBcpu_pct: 620.62 %temperature_c: 47 °Creal_time_factor: 0.0552 ratio
2026-07-31T08:36:53Z
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-medium-pt-batchfaster-whisper / whisper-mediumcudanvidia-rtx-4090fleurs-pt
cer: 0.0036 ratiower: 0.0137 ratioram_mb: 1912.68 MBcpu_pct: 560.45 %temperature_c: 46 °Creal_time_factor: 0.0395 ratio
2026-07-31T08:37:23Z
details
Profile
whisper-medium-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-small-de-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090fleurs-de
cer: 0.0133 ratiower: 0.0400 ratioram_mb: 1110.47 MBcpu_pct: 702.47 %temperature_c: 46 °Creal_time_factor: 0.0257 ratio
2026-07-31T08:37:44Z
details
Profile
whisper-small-de-batch@1.1.0
Pack
fleurs-de@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-small-en-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090librispeech-en
cer: 0.0357 ratiower: 0.0896 ratioram_mb: 981.93 MBcpu_pct: 878.63 %temperature_c: 46.50 °Creal_time_factor: 0.0310 ratio
2026-07-31T08:37:59Z
details
Profile
whisper-small-en-batch@1.1.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-small-es-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090fleurs-es
cer: 0.0122 ratiower: 0.0427 ratioram_mb: 983.17 MBcpu_pct: 838.53 %temperature_c: 46.50 °Creal_time_factor: 0.0291 ratio
2026-07-31T08:38:15Z
details
Profile
whisper-small-es-batch@1.1.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-small-fr-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090fleurs-fr
cer: 0.0425 ratiower: 0.1173 ratioram_mb: 1027.13 MBcpu_pct: 803.64 %temperature_c: 48 °Creal_time_factor: 0.0349 ratio
2026-07-31T08:38:32Z
details
Profile
whisper-small-fr-batch@1.1.0
Pack
fleurs-fr@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-small-nl-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090fleurs-nl
cer: 0.0462 ratiower: 0.1679 ratioram_mb: 1048.79 MBcpu_pct: 872.14 %temperature_c: 47 °Creal_time_factor: 0.0392 ratio
2026-07-31T08:38:47Z
details
Profile
whisper-small-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-small-pt-batchfaster-whisper / whisper-smallcudanvidia-rtx-4090fleurs-pt
cer: 0.0045 ratiower: 0.0219 ratioram_mb: 1023.77 MBcpu_pct: 748.90 %temperature_c: 47 °Creal_time_factor: 0.0283 ratio
2026-07-31T08:39:05Z
details
Profile
whisper-small-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-tiny-de-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090fleurs-de
cer: 0.0477 ratiower: 0.1720 ratioram_mb: 717.94 MBcpu_pct: 1394.40 %temperature_c: 47.50 °Creal_time_factor: 0.0168 ratio
2026-07-31T08:39:14Z
details
Profile
whisper-tiny-de-batch@1.1.0
Pack
fleurs-de@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-tiny-en-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090librispeech-en
cer: 0.0520 ratiower: 0.1194 ratioram_mb: 732.55 MBcpu_pct: 1248.97 %temperature_c: 51 °Creal_time_factor: 0.0206 ratio
2026-07-31T08:39:23Z
details
Profile
whisper-tiny-en-batch@1.1.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-tiny-es-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090fleurs-es
cer: 0.0263 ratiower: 0.0940 ratioram_mb: 705.13 MBcpu_pct: 1202.67 %temperature_c: 48 °Creal_time_factor: 0.0198 ratio
2026-07-31T08:39:33Z
details
Profile
whisper-tiny-es-batch@1.1.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-tiny-fr-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090fleurs-fr
cer: 0.1330 ratiower: 0.3812 ratioram_mb: 698.85 MBcpu_pct: 1184.64 %temperature_c: 47.50 °Creal_time_factor: 0.0231 ratio
2026-07-31T08:39:43Z
details
Profile
whisper-tiny-fr-batch@1.1.0
Pack
fleurs-fr@1.0.0
Repeats
2
Backend
cuda
beam_size
5
quantization
int8
threads
4
vad
true
whisper-tiny-nl-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090fleurs-nl
cer: 0.1900 ratiower: 0.4891 ratioram_mb: 713.65 MBcpu_pct: 1268.28 %temperature_c: 48.50 °Creal_time_factor: 0.0264 ratio
2026-07-31T08:39:52Z
details
Profile
whisper-tiny-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-tiny-pt-batchfaster-whisper / whisper-tinycudanvidia-rtx-4090fleurs-pt
cer: 0.0286 ratiower: 0.1148 ratioram_mb: 718.45 MBcpu_pct: 1140.89 %temperature_c: 48 °Creal_time_factor: 0.0192 ratio
2026-07-31T08:40:02Z
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

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

* profile default

26–40 of 40
← PrevPage 2 of 2Next →