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)
StreamingStreaming results only — real-time factor doesn't apply, so batch results never appear here.
AnyBatchStreamingConcurrency

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

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
whisper-large-v3-es-streamingfaster-whisper / whisper-large-v3apple-m1-profleurs-es
wer: 0.0313 ratioram_mb: 3758.84 MBcpu_pct: 427.98 %real_time_factor: 4.16 ratioupdate_frequency: 1.12 Hzpartial_stability: 0.8860 ratiofirst_final_latency: 7733.59 msend_of_speech_latency: 5610.75 msfirst_partial_latency: 5245.80 msstreaming_responsiveness: 0.1921 index
2026-08-03T10:54:20Z
details
Profile
whisper-large-v3-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true
whisper-medium-es-streamingfaster-whisper / whisper-mediumapple-m1-profleurs-es
wer: 0.0427 ratioram_mb: 2117.15 MBcpu_pct: 444.97 %real_time_factor: 2.28 ratioupdate_frequency: 1.11 Hzpartial_stability: 0.8965 ratiofirst_final_latency: 6852.49 msend_of_speech_latency: 3473.60 msfirst_partial_latency: 3122.66 msstreaming_responsiveness: 0.3155 index
2026-08-03T12:39:51Z
details
Profile
whisper-medium-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
beam_size
5
chunk_ms
1000
quantization
int8
threads
4
vad
true
vosk-medium-es-streamingvosk / vosk-model-es-0.42apple-m1-profleurs-es
wer: 0.0313 ratioram_mb: 4547.58 MBcpu_pct: 78.49 %real_time_factor: 0.0449 ratioupdate_frequency: 1.17 Hzpartial_stability: 0.9782 ratiofirst_final_latency: 9810.26 msend_of_speech_latency: 1407.94 msfirst_partial_latency: 1749.34 msstreaming_responsiveness: 0.6388 index
2026-08-03T13:59:23Z
details
Profile
vosk-medium-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
chunk_ms
1000
whispercpp-large-v3-es-streamingwhisper-cpp / whisper-large-v3metalapple-m1-profleurs-es
wer: 0.0399 ratioram_mb: 4063.33 MBcpu_pct: 8.20 %real_time_factor: 1.07 ratioupdate_frequency: 0.9534 Hzpartial_stability: 0.9450 ratiofirst_final_latency: 5233.96 msend_of_speech_latency: 2160.05 msfirst_partial_latency: 1734.84 msstreaming_responsiveness: 0.5007 index
2026-08-03T14:27:31Z
details
Profile
whispercpp-large-v3-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
metal
chunk_ms
1000
threads
4

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

* profile default