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

ProfileRuntime / ModelHardwarePackMetricsSubmittedDetails
vosk-medium-es-streamingvosk / vosk-model-es-0.42amd-ryzen-9-9950xfleurs-es
wer: 0.0313 ratioram_mb: 4237.47 MBcpu_pct: 74.54 %real_time_factor: 0.1213 ratioupdate_frequency: 1.17 Hzpartial_stability: 0.9782 ratiofirst_final_latency: 9973.29 msend_of_speech_latency: 1571.56 msfirst_partial_latency: 1814.01 msstreaming_responsiveness: 0.6183 index
2026-08-03T11:25:48Z
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-v3amd-ryzen-9-9950xfleurs-es
wer: 0.0399 ratioram_mb: 3986.15 MBcpu_pct: 400.33 %real_time_factor: 10.76 ratioupdate_frequency: 0.9534 Hzpartial_stability: 0.9450 ratiofirst_final_latency: 14638.63 msend_of_speech_latency: 11390.87 msfirst_partial_latency: 10414.33 msstreaming_responsiveness: 0.0862 index
2026-08-03T14:49:42Z
details
Profile
whispercpp-large-v3-es-streaming@1.0.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
chunk_ms
1000
threads
4

Constant across this view: chunk_ms 1000 · threads 4

* profile default