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 →
BatchBatch results only — streaming uses different metrics and never appears here.
Sorted by most recently submitted · 25 results · click a metric below to sort by it
| Profile | Runtime / Model | Hardware | Pack | Metrics | Submitted | Details |
|---|---|---|---|---|---|---|
| whisper-medium-de-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | fleurs-de | 2026-07-31T08:35:01Z | details
| |
| whisper-medium-en-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | librispeech-en | 2026-07-31T08:35:28Z | details
| |
| whisper-medium-es-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | fleurs-es | 2026-07-31T08:35:56Z | details
| |
| whisper-medium-fr-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | fleurs-fr | 2026-07-31T08:36:25Z | details
| |
| whisper-medium-nl-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | fleurs-nl | 2026-07-31T08:36:53Z | details
| |
| whisper-medium-pt-batch | faster-whisper / whisper-mediumcuda | nvidia-rtx-4090 | fleurs-pt | 2026-07-31T08:37:23Z | details
| |
| whisper-small-de-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | fleurs-de | 2026-07-31T08:37:44Z | details
| |
| whisper-small-en-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | librispeech-en | 2026-07-31T08:37:59Z | details
| |
| whisper-small-es-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | fleurs-es | 2026-07-31T08:38:15Z | details
| |
| whisper-small-fr-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | fleurs-fr | 2026-07-31T08:38:32Z | details
| |
| whisper-small-nl-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | fleurs-nl | 2026-07-31T08:38:47Z | details
| |
| whisper-small-pt-batch | faster-whisper / whisper-smallcuda | nvidia-rtx-4090 | fleurs-pt | 2026-07-31T08:39:05Z | details
| |
| whisper-tiny-de-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | fleurs-de | 2026-07-31T08:39:14Z | details
| |
| whisper-tiny-en-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | librispeech-en | 2026-07-31T08:39:23Z | details
| |
| whisper-tiny-es-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | fleurs-es | 2026-07-31T08:39:33Z | details
| |
| whisper-tiny-fr-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | fleurs-fr | 2026-07-31T08:39:43Z | details
| |
| whisper-tiny-nl-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | fleurs-nl | 2026-07-31T08:39:52Z | details
| |
| whisper-tiny-pt-batch | faster-whisper / whisper-tinycuda | nvidia-rtx-4090 | fleurs-pt | 2026-07-31T08:40:02Z | details
| |
| vosk-small-de-batch | vosk / vosk-model-small-de-0.15 | intel-xeon-e5-2680-v4 | fleurs-de | 2026-07-31T08:40:33Z | details
| |
| vosk-small-en-batch | vosk / vosk-model-small-en-us-0.15 | intel-xeon-e5-2680-v4 | librispeech-en | 2026-07-31T08:41:19Z | details
| |
| vosk-small-es-batch | vosk / vosk-model-small-es-0.42 | intel-xeon-e5-2680-v4 | fleurs-es | 2026-07-31T08:41:46Z | details
| |
| vosk-small-fr-batch | vosk / vosk-model-small-fr-0.22 | intel-xeon-e5-2680-v4 | fleurs-fr | 2026-07-31T08:43:09Z | details
| |
| vosk-small-nl-batch | vosk / vosk-model-small-nl-0.22 | intel-xeon-e5-2680-v4 | fleurs-nl | 2026-07-31T08:44:51Z | details
| |
| vosk-small-pt-batch | vosk / vosk-model-small-pt-0.3 | intel-xeon-e5-2680-v4 | fleurs-pt | 2026-07-31T08:46:13Z | details
| |
| whispercpp-base-de-batch | whisper-cpp / whisper-base | intel-xeon-e5-2680-v4 | fleurs-de | 2026-07-31T08:47:40Z | details
|
Constant across this view: beam_size 5 · quantization int8 · threads 4 · vad true
* profile default