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 →

AnyEvery verified result, batch and streaming mixed together.

Sorted by most recently submitted · 25 results · click a metric below to sort by it

ProfileRuntime / ModelHardwarePackconcurrencyMetricsSubmittedDetails
whispercpp-small-de-batchwhisper-cpp / whisper-smallamd-epyc-9135fleurs-de2026-08-01T14:32:24Z
details
Profile
whispercpp-small-de-batch@1.1.0
Pack
fleurs-de@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-small-en-batchwhisper-cpp / whisper-small.enamd-epyc-9135librispeech-en2026-08-01T14:34:59Z
details
Profile
whispercpp-small-en-batch@1.1.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-small-es-batchwhisper-cpp / whisper-smallamd-epyc-9135fleurs-es2026-08-01T14:36:04Z
details
Profile
whispercpp-small-es-batch@1.1.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-small-fr-batchwhisper-cpp / whisper-smallamd-epyc-9135fleurs-fr2026-08-01T14:37:10Z
details
Profile
whispercpp-small-fr-batch@1.1.0
Pack
fleurs-fr@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-small-nl-batchwhisper-cpp / whisper-smallamd-epyc-9135fleurs-nl2026-08-01T14:38:13Z
details
Profile
whispercpp-small-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-small-pt-batchwhisper-cpp / whisper-smallamd-epyc-9135fleurs-pt2026-08-01T14:39:18Z
details
Profile
whispercpp-small-pt-batch@1.1.0
Pack
fleurs-pt@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-de-batchwhisper-cpp / whisper-tinyamd-epyc-9135fleurs-de2026-08-01T14:39:30Z
details
Profile
whispercpp-tiny-de-batch@1.1.0
Pack
fleurs-de@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-en-batchwhisper-cpp / whisper-tiny.enamd-epyc-9135librispeech-en2026-08-01T14:39:42Z
details
Profile
whispercpp-tiny-en-batch@1.1.0
Pack
librispeech-en@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-es-batchwhisper-cpp / whisper-tinyamd-epyc-9135fleurs-es2026-08-01T14:39:52Z
details
Profile
whispercpp-tiny-es-batch@1.1.0
Pack
fleurs-es@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-fr-batchwhisper-cpp / whisper-tinyamd-epyc-9135fleurs-fr2026-08-01T14:40:03Z
details
Profile
whispercpp-tiny-fr-batch@1.1.0
Pack
fleurs-fr@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-nl-batchwhisper-cpp / whisper-tinyamd-epyc-9135fleurs-nl2026-08-01T14:40:14Z
details
Profile
whispercpp-tiny-nl-batch@1.1.0
Pack
fleurs-nl@1.0.0
Repeats
2
Backend
cpu
threads
4
whispercpp-tiny-pt-batchwhisper-cpp / whisper-tinyamd-epyc-9135fleurs-pt2026-08-01T14:40:24Z
details
Profile
whispercpp-tiny-pt-batch@1.1.0
Pack
fleurs-pt@1.0.0
Repeats
2
Backend
cpu
threads
4
whisper-base-concurrencyfaster-whisper / whisper-basecudanvidia-rtx-5090librispeech-en1 *2026-08-01T14:52:20Z
details
Profile
whisper-base-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-base-concurrencyfaster-whisper / whisper-basecudanvidia-rtx-5090librispeech-en22026-08-01T14:53:22Z
details
Profile
whisper-base-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-base-concurrencyfaster-whisper / whisper-basecudanvidia-rtx-5090librispeech-en42026-08-01T14:54:25Z
details
Profile
whisper-base-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-base-concurrencyfaster-whisper / whisper-basecudanvidia-rtx-5090librispeech-en82026-08-01T14:55:29Z
details
Profile
whisper-base-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-large-v3-concurrencyfaster-whisper / whisper-large-v3cudanvidia-rtx-5090librispeech-en1 *2026-08-01T14:56:38Z
details
Profile
whisper-large-v3-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-large-v3-concurrencyfaster-whisper / whisper-large-v3cudanvidia-rtx-5090librispeech-en22026-08-01T14:57:49Z
details
Profile
whisper-large-v3-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-large-v3-concurrencyfaster-whisper / whisper-large-v3cudanvidia-rtx-5090librispeech-en42026-08-01T14:59:00Z
details
Profile
whisper-large-v3-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-large-v3-concurrencyfaster-whisper / whisper-large-v3cudanvidia-rtx-5090librispeech-en82026-08-01T15:00:13Z
details
Profile
whisper-large-v3-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-medium-concurrencyfaster-whisper / whisper-mediumcudanvidia-rtx-5090librispeech-en1 *2026-08-01T15:01:20Z
details
Profile
whisper-medium-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-medium-concurrencyfaster-whisper / whisper-mediumcudanvidia-rtx-5090librispeech-en22026-08-01T15:02:27Z
details
Profile
whisper-medium-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-medium-concurrencyfaster-whisper / whisper-mediumcudanvidia-rtx-5090librispeech-en42026-08-01T15:03:34Z
details
Profile
whisper-medium-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-medium-concurrencyfaster-whisper / whisper-mediumcudanvidia-rtx-5090librispeech-en82026-08-01T15:04:44Z
details
Profile
whisper-medium-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-small-concurrencyfaster-whisper / whisper-smallcudanvidia-rtx-5090librispeech-en1 *2026-08-01T15:05:47Z
details
Profile
whisper-small-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

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

* profile default

151175 of 556
← PrevPage 7 of 23Next →