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

ProfileRuntime / ModelHardwarePackconcurrencyMetricsSubmittedDetails
whisper-small-concurrencyfaster-whisper / whisper-smallcudanvidia-rtx-5090librispeech-en2
ram_mb: 1160.53 MBcpu_pct: 574.03 %throughput: 52.08 audio-s/stemperature_c: 55.19 °Creal_time_factor: 0.0457 ratio
2026-08-01T15:06:52Z
details
Profile
whisper-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
2 (default 1)
quantization
int8
threads
4
vad
true
whisper-small-concurrencyfaster-whisper / whisper-smallcudanvidia-rtx-5090librispeech-en4
ram_mb: 1222.39 MBcpu_pct: 594.90 %throughput: 58.60 audio-s/stemperature_c: 54.19 °Creal_time_factor: 0.0801 ratio
2026-08-01T15:07:56Z
details
Profile
whisper-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
4 (default 1)
quantization
int8
threads
4
vad
true
whisper-small-concurrencyfaster-whisper / whisper-smallcudanvidia-rtx-5090librispeech-en8
ram_mb: 1303.44 MBcpu_pct: 603.23 %throughput: 55.05 audio-s/stemperature_c: 53.63 °Creal_time_factor: 0.1670 ratio
2026-08-01T15:09:02Z
details
Profile
whisper-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
8 (default 1)
quantization
int8
threads
4
vad
true
whisper-tiny-concurrencyfaster-whisper / whisper-tinycudanvidia-rtx-5090librispeech-en1 *
ram_mb: 854.65 MBcpu_pct: 634.52 %throughput: 52.01 audio-s/stemperature_c: 55.75 °Creal_time_factor: 0.0225 ratio
2026-08-01T15:10:04Z
details
Profile
whisper-tiny-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
1
quantization
int8
threads
4
vad
true
whisper-tiny-concurrencyfaster-whisper / whisper-tinycudanvidia-rtx-5090librispeech-en2
ram_mb: 905.04 MBcpu_pct: 668.18 %throughput: 72.35 audio-s/stemperature_c: 54.81 °Creal_time_factor: 0.0338 ratio
2026-08-01T15:11:07Z
details
Profile
whisper-tiny-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
2 (default 1)
quantization
int8
threads
4
vad
true
whisper-tiny-concurrencyfaster-whisper / whisper-tinycudanvidia-rtx-5090librispeech-en4
ram_mb: 979.58 MBcpu_pct: 656.53 %throughput: 80.08 audio-s/stemperature_c: 56.38 °Creal_time_factor: 0.0629 ratio
2026-08-01T15:12:09Z
details
Profile
whisper-tiny-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
4 (default 1)
quantization
int8
threads
4
vad
true
whisper-tiny-concurrencyfaster-whisper / whisper-tinycudanvidia-rtx-5090librispeech-en8
ram_mb: 1146.46 MBcpu_pct: 681.02 %throughput: 81.82 audio-s/stemperature_c: 57.25 °Creal_time_factor: 0.1192 ratio
2026-08-01T15:13:12Z
details
Profile
whisper-tiny-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cuda
beam_size
5
concurrency
8 (default 1)
quantization
int8
threads
4
vad
true
vosk-medium-concurrencyvosk / vosk-model-en-us-0.22amd-epyc-9135librispeech-en1 *
ram_mb: 6418.31 MBcpu_pct: 104.85 %throughput: 6.43 audio-s/stemperature_c: 57.06 °Creal_time_factor: 0.1693 ratio
2026-08-01T15:14:29Z
details
Profile
vosk-medium-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
1
vosk-medium-concurrencyvosk / vosk-model-en-us-0.22amd-epyc-9135librispeech-en2
ram_mb: 11271.62 MBcpu_pct: 179.26 %throughput: 12.67 audio-s/stemperature_c: 56.50 °Creal_time_factor: 0.1668 ratio
2026-08-01T15:15:53Z
details
Profile
vosk-medium-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
2 (default 1)
vosk-medium-concurrencyvosk / vosk-model-en-us-0.22amd-epyc-9135librispeech-en4
ram_mb: 21533.44 MBcpu_pct: 281.62 %throughput: 24.63 audio-s/stemperature_c: 55.75 °Creal_time_factor: 0.1703 ratio
2026-08-01T15:17:40Z
details
Profile
vosk-medium-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
4 (default 1)
vosk-medium-concurrencyvosk / vosk-model-en-us-0.22amd-epyc-9135librispeech-en8
ram_mb: 40505.18 MBcpu_pct: 415.93 %throughput: 46.71 audio-s/stemperature_c: 57.13 °Creal_time_factor: 0.1793 ratio
2026-08-01T15:19:55Z
details
Profile
vosk-medium-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
8 (default 1)
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en1 *
ram_mb: 290.53 MBcpu_pct: 103.25 %throughput: 11.76 audio-s/stemperature_c: 55.69 °Creal_time_factor: 0.0961 ratio
2026-08-01T15:21:00Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
1
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en2
ram_mb: 487.61 MBcpu_pct: 200.24 %throughput: 22.75 audio-s/stemperature_c: 53.75 °Creal_time_factor: 0.0958 ratio
2026-08-01T15:22:03Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
2 (default 1)
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en4
ram_mb: 899.12 MBcpu_pct: 389.02 %throughput: 43.29 audio-s/stemperature_c: 55.75 °Creal_time_factor: 0.0998 ratio
2026-08-01T15:23:07Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
4 (default 1)
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en8
ram_mb: 1730.67 MBcpu_pct: 712.03 %throughput: 78.62 audio-s/stemperature_c: 57.31 °Creal_time_factor: 0.1115 ratio
2026-08-01T15:24:14Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
8 (default 1)
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en12
ram_mb: 2399.07 MBcpu_pct: 692.13 %throughput: 78.12 audio-s/stemperature_c: 57.31 °Creal_time_factor: 0.1701 ratio
2026-08-01T15:25:24Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
12 (default 1)
vosk-small-concurrencyvosk / vosk-model-small-en-us-0.15amd-epyc-9135librispeech-en16
ram_mb: 3210.26 MBcpu_pct: 683.93 %throughput: 69.58 audio-s/stemperature_c: 56.50 °Creal_time_factor: 0.2571 ratio
2026-08-01T15:26:36Z
details
Profile
vosk-small-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
16 (default 1)
whispercpp-base-concurrencywhisper-cpp / whisper-baseamd-epyc-9135librispeech-en1 *
ram_mb: 329.56 MBcpu_pct: 401.30 %throughput: 19.46 audio-s/stemperature_c: 57.13 °Creal_time_factor: 0.0754 ratio
2026-08-01T15:27:39Z
details
Profile
whispercpp-base-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
1
threads
4
whispercpp-base-concurrencywhisper-cpp / whisper-baseamd-epyc-9135librispeech-en2
ram_mb: 574.33 MBcpu_pct: 767.12 %throughput: 36.22 audio-s/stemperature_c: 60.19 °Creal_time_factor: 0.0812 ratio
2026-08-01T15:28:41Z
details
Profile
whispercpp-base-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
2 (default 1)
threads
4
whispercpp-base-concurrencywhisper-cpp / whisper-baseamd-epyc-9135librispeech-en4
ram_mb: 1070.32 MBcpu_pct: 764.57 %throughput: 33.50 audio-s/stemperature_c: 59.13 °Creal_time_factor: 0.1741 ratio
2026-08-01T15:29:43Z
details
Profile
whispercpp-base-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
4 (default 1)
threads
4
whispercpp-base-concurrencywhisper-cpp / whisper-baseamd-epyc-9135librispeech-en8
ram_mb: 2066.03 MBcpu_pct: 770.50 %throughput: 28.53 audio-s/stemperature_c: 56.13 °Creal_time_factor: 0.4175 ratio
2026-08-01T15:30:49Z
details
Profile
whispercpp-base-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
8 (default 1)
threads
4
whispercpp-large-v3-concurrencywhisper-cpp / whisper-large-v3amd-epyc-9135librispeech-en1 *
ram_mb: 3504.12 MBcpu_pct: 233.54 %throughput: 0.7718 audio-s/stemperature_c: 59.81 °Creal_time_factor: 1.76 ratio
2026-08-01T15:35:21Z
details
Profile
whispercpp-large-v3-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
1
threads
4
whispercpp-large-v3-concurrencywhisper-cpp / whisper-large-v3amd-epyc-9135librispeech-en2
ram_mb: 6921.20 MBcpu_pct: 727.96 %throughput: 2.38 audio-s/stemperature_c: 60 °Creal_time_factor: 1.47 ratio
2026-08-01T15:36:46Z
details
Profile
whispercpp-large-v3-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
2 (default 1)
threads
4
whispercpp-large-v3-concurrencywhisper-cpp / whisper-large-v3amd-epyc-9135librispeech-en4
ram_mb: 13752.28 MBcpu_pct: 719.66 %throughput: 2.88 audio-s/stemperature_c: 59.50 °Creal_time_factor: 3.25 ratio
2026-08-01T15:38:47Z
details
Profile
whispercpp-large-v3-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
4 (default 1)
threads
4
whispercpp-large-v3-concurrencywhisper-cpp / whisper-large-v3amd-epyc-9135librispeech-en8
ram_mb: 27396.48 MBcpu_pct: 708.95 %throughput: 2.88 audio-s/stemperature_c: 57.06 °Creal_time_factor: 8.45 ratio
2026-08-01T15:41:27Z
details
Profile
whispercpp-large-v3-concurrency@1.0.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
concurrency
8 (default 1)
threads
4

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

* profile default

176–200 of 556
← PrevPage 8 of 23Next →