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 energy Fastest (lowest RTF)Most accurate (lowest WER)

BatchBatch results only — streaming uses different metrics and never appears here.

Any Batch Streaming Concurrency

Backend: cuda

LanguagePackRuntimeModelBackendHardware

Clear + Add filter

Quality gates:WER < 5%WER < 10%WER < 15%

custom…

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

Profile	Runtime / Model	Hardware	Pack	Metrics	Submitted	Details
whisper-tiny-en-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-5090	librispeech-en	cer: 0.0514 ratio wer: 0.1104 ratio ram_mb: 865.29 MB cpu_pct: 585.97 %temperature_c: 53.25 °C real_time_factor: 0.0205 ratio	2026-08-01T14:02:28Z	details Profile whisper-tiny-en-batch@1.1.0 Pack librispeech-en@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-es-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-5090	fleurs-es	cer: 0.0263 ratio wer: 0.0997 ratio ram_mb: 798.54 MB cpu_pct: 543.39 %temperature_c: 53 °C real_time_factor: 0.0187 ratio	2026-08-01T14:02:37Z	details Profile whisper-tiny-es-batch@1.1.0 Pack fleurs-es@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-fr-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-5090	fleurs-fr	cer: 0.1334 ratio wer: 0.4047 ratio ram_mb: 829.09 MB cpu_pct: 516.24 %temperature_c: 55 °C real_time_factor: 0.0205 ratio	2026-08-01T14:02:45Z	details Profile whisper-tiny-fr-batch@1.1.0 Pack fleurs-fr@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-nl-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-5090	fleurs-nl	cer: 0.1955 ratio wer: 0.4708 ratio ram_mb: 830.74 MB cpu_pct: 531.77 %temperature_c: 55 °C real_time_factor: 0.0252 ratio	2026-08-01T14:02:53Z	details Profile whisper-tiny-nl-batch@1.1.0 Pack fleurs-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-pt-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-5090	fleurs-pt	cer: 0.0309 ratio wer: 0.1230 ratio ram_mb: 798.13 MB cpu_pct: 505.11 %temperature_c: 53.19 °C real_time_factor: 0.0176 ratio	2026-08-01T14:03:01Z	details Profile whisper-tiny-pt-batch@1.1.0 Pack fleurs-pt@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-nl-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	common-voice-nl	cer: 0.1741 ratio wer: 0.4000 ratio ram_mb: 873.35 MB cpu_pct: 1427.05 %temperature_c: 49 °C real_time_factor: 0.0301 ratio	2026-07-31T12:31:48Z	details Profile whisper-base-nl-batch@1.1.0 Pack common-voice-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-nl-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	common-voice-nl-elderly	cer: 0.0644 ratio wer: 0.2216 ratio ram_mb: 860.05 MB cpu_pct: 1524.98 %temperature_c: 50.50 °C real_time_factor: 0.0260 ratio	2026-07-31T12:32:30Z	details Profile whisper-base-nl-batch@1.1.0 Pack common-voice-nl-elderly@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-nl-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	common-voice-nl	cer: 0.0512 ratio wer: 0.1121 ratio ram_mb: 3422.53 MB cpu_pct: 761.44 %temperature_c: 49.50 °C real_time_factor: 0.0642 ratio	2026-07-31T12:33:32Z	details Profile whisper-large-v3-nl-batch@1.1.0 Pack common-voice-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-nl-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	common-voice-nl-elderly	cer: 0.0073 ratio wer: 0.0264 ratio ram_mb: 3448.98 MB cpu_pct: 754.01 %temperature_c: 49.50 °C real_time_factor: 0.0532 ratio	2026-07-31T12:34:35Z	details Profile whisper-large-v3-nl-batch@1.1.0 Pack common-voice-nl-elderly@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-medium-nl-batch	faster-whisper / whisper-mediumcuda	nvidia-rtx-4090	common-voice-nl	cer: 0.0686 ratio wer: 0.1879 ratio ram_mb: 1958.74 MB cpu_pct: 786.81 %temperature_c: 49.50 °C real_time_factor: 0.0548 ratio	2026-07-31T12:35:17Z	details Profile whisper-medium-nl-batch@1.1.0 Pack common-voice-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-medium-nl-batch	faster-whisper / whisper-mediumcuda	nvidia-rtx-4090	common-voice-nl-elderly	cer: 0.0116 ratio wer: 0.0422 ratio ram_mb: 1894.50 MB cpu_pct: 875.91 %temperature_c: 50.50 °C real_time_factor: 0.0453 ratio	2026-07-31T12:36:00Z	details Profile whisper-medium-nl-batch@1.1.0 Pack common-voice-nl-elderly@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-small-nl-batch	faster-whisper / whisper-smallcuda	nvidia-rtx-4090	common-voice-nl	cer: 0.0763 ratio wer: 0.2182 ratio ram_mb: 1060.16 MB cpu_pct: 1102.41 %temperature_c: 52 °C real_time_factor: 0.0388 ratio	2026-07-31T12:36:24Z	details Profile whisper-small-nl-batch@1.1.0 Pack common-voice-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-small-nl-batch	faster-whisper / whisper-smallcuda	nvidia-rtx-4090	common-voice-nl-elderly	cer: 0.0284 ratio wer: 0.1108 ratio ram_mb: 1049.66 MB cpu_pct: 1219.30 %temperature_c: 51.50 °C real_time_factor: 0.0327 ratio	2026-07-31T12:36:49Z	details Profile whisper-small-nl-batch@1.1.0 Pack common-voice-nl-elderly@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-nl-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-4090	common-voice-nl	cer: 0.2698 ratio wer: 0.5758 ratio ram_mb: 702.93 MB cpu_pct: 1495.73 %temperature_c: 53 °C real_time_factor: 0.0261 ratio	2026-07-31T12:37:04Z	details Profile whisper-tiny-nl-batch@1.1.0 Pack common-voice-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-tiny-nl-batch	faster-whisper / whisper-tinycuda	nvidia-rtx-4090	common-voice-nl-elderly	cer: 0.1306 ratio wer: 0.3799 ratio ram_mb: 703.05 MB cpu_pct: 1731.26 %temperature_c: 53.50 °C real_time_factor: 0.0228 ratio	2026-07-31T12:37:20Z	details Profile whisper-tiny-nl-batch@1.1.0 Pack common-voice-nl-elderly@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-de-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	fleurs-de	cer: 0.0260 ratio wer: 0.0840 ratio ram_mb: 836.88 MB cpu_pct: 993.48 %temperature_c: 44 °C real_time_factor: 0.0194 ratio	2026-07-31T08:27:02Z	details Profile whisper-base-de-batch@1.1.0 Pack fleurs-de@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-en-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	librispeech-en	cer: 0.0390 ratio wer: 0.0896 ratio ram_mb: 787.38 MB cpu_pct: 1183.06 %temperature_c: 44.50 °C real_time_factor: 0.0226 ratio	2026-07-31T08:28:14Z	details Profile whisper-base-en-batch@1.1.0 Pack librispeech-en@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-es-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	fleurs-es	cer: 0.0164 ratio wer: 0.0712 ratio ram_mb: 775.86 MB cpu_pct: 1100.00 %temperature_c: 44 °C real_time_factor: 0.0214 ratio	2026-07-31T08:28:41Z	details Profile whisper-base-es-batch@1.1.0 Pack fleurs-es@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-fr-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	fleurs-fr	cer: 0.0683 ratio wer: 0.1965 ratio ram_mb: 772.98 MB cpu_pct: 1083.71 %temperature_c: 45 °C real_time_factor: 0.0253 ratio	2026-07-31T08:28:58Z	details Profile whisper-base-fr-batch@1.1.0 Pack fleurs-fr@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-nl-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	fleurs-nl	cer: 0.1014 ratio wer: 0.3248 ratio ram_mb: 773.73 MB cpu_pct: 1199.21 %temperature_c: 45.50 °C real_time_factor: 0.0278 ratio	2026-07-31T08:29:08Z	details Profile whisper-base-nl-batch@1.1.0 Pack fleurs-nl@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-base-pt-batch	faster-whisper / whisper-basecuda	nvidia-rtx-4090	fleurs-pt	cer: 0.0182 ratio wer: 0.0628 ratio ram_mb: 776.64 MB cpu_pct: 1049.89 %temperature_c: 46.50 °C real_time_factor: 0.0212 ratio	2026-07-31T08:29:32Z	details Profile whisper-base-pt-batch@1.1.0 Pack fleurs-pt@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-de-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	fleurs-de	cer: 0.0054 ratio wer: 0.0160 ratio ram_mb: 3710.72 MB cpu_pct: 381.07 %temperature_c: 45 °C real_time_factor: 0.0430 ratio	2026-07-31T08:30:41Z	details Profile whisper-large-v3-de-batch@1.1.0 Pack fleurs-de@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-en-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	librispeech-en	cer: 0.0276 ratio wer: 0.0597 ratio ram_mb: 3486.19 MB cpu_pct: 516.14 %temperature_c: 45 °C real_time_factor: 0.0498 ratio	2026-07-31T08:31:23Z	details Profile whisper-large-v3-en-batch@1.1.0 Pack librispeech-en@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-es-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	fleurs-es	cer: 0.0052 ratio wer: 0.0085 ratio ram_mb: 3431.49 MB cpu_pct: 480.53 %temperature_c: 46 °C real_time_factor: 0.0495 ratio	2026-07-31T08:32:07Z	details Profile whisper-large-v3-es-batch@1.1.0 Pack fleurs-es@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true
whisper-large-v3-fr-batch	faster-whisper / whisper-large-v3cuda	nvidia-rtx-4090	fleurs-fr	cer: 0.0118 ratio wer: 0.0411 ratio ram_mb: 3442.75 MB cpu_pct: 467.83 %temperature_c: 46 °C real_time_factor: 0.0597 ratio	2026-07-31T08:32:51Z	details Profile whisper-large-v3-fr-batch@1.1.0 Pack fleurs-fr@1.0.0 Repeats 2 Backend cuda beam_size 5 quantization int8 threads 4 vad true

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

* profile default

26–50 of 110

← PrevPage 2 of 5Next →