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

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
whisper-small-de-streamingfaster-whisper / whisper-smallcudanvidia-rtx-4060-ti-16gbfleurs-de
wer: 0.0880 ratioram_mb: 1123.94 MBcpu_pct: 884.98 %real_time_factor: 0.1087 ratioupdate_frequency: 1.21 Hzpartial_stability: 0.8653 ratiofirst_final_latency: 3054.25 msend_of_speech_latency: 2561.38 msfirst_partial_latency: 1029.70 msstreaming_responsiveness: 1.09 index
2026-08-03T11:08:21Z
details
Profile
whisper-small-de-streaming@1.0.0
Pack
fleurs-de@1.0.0
Repeats
2
Backend
cuda
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true
whisper-small-en-streamingfaster-whisper / whisper-smallcudanvidia-rtx-4060-ti-16gblibrispeech-en
wer: 0.1284 ratioram_mb: 988.37 MBcpu_pct: 1003.73 %real_time_factor: 0.1324 ratioupdate_frequency: 1.07 Hzpartial_stability: 0.8947 ratiofirst_final_latency: 2961.21 msend_of_speech_latency: 755.83 msfirst_partial_latency: 919.92 msstreaming_responsiveness: 1.06 index
2026-08-03T11:09:04Z
details
Profile
whisper-small-en-streaming@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true
whisper-small-es-streamingfaster-whisper / whisper-smallcudanvidia-rtx-4060-ti-16gbfleurs-es
wer: 0.0912 ratioram_mb: 986.97 MBcpu_pct: 1004.53 %real_time_factor: 0.1161 ratioupdate_frequency: 1.17 Hzpartial_stability: 0.8779 ratiofirst_final_latency: 3718.84 msend_of_speech_latency: 1557.77 msfirst_partial_latency: 1284.20 msstreaming_responsiveness: 0.8197 index
2026-08-03T11:09:48Z
details
Profile
whisper-small-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cuda
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true
whisper-small-pt-streamingfaster-whisper / whisper-smallcudanvidia-rtx-4060-ti-16gbfleurs-pt
wer: 0.1148 ratioram_mb: 999.96 MBcpu_pct: 1000.75 %real_time_factor: 0.1270 ratioupdate_frequency: 1.10 Hzpartial_stability: 0.8380 ratiofirst_final_latency: 3270.96 msend_of_speech_latency: 1547.98 msfirst_partial_latency: 1363.20 msstreaming_responsiveness: 0.7873 index
2026-08-03T11:12:04Z
details
Profile
whisper-small-pt-streaming@1.0.0
Pack
fleurs-pt@1.0.0
Repeats
2
Backend
cuda
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true

Constant across this view: beam_size 5 · chunk_ms 1000 · quantization int8 · threads 4 · vad true

* profile default

26–29 of 29
← PrevPage 2 of 2Next →