Systran/faster-whisper-large-v3

whisper-http unknown on 1x NVIDIA RTX 4000 Ada Generation Laptop GPU (fp16) · seed 0 · run 019e5ff4-79e4-7403-aa27-603a8fd37d02 · signed

Headline metrics

TTFT P50 (ms)	—
TTFT P99 (ms)	—
Throughput (tok/s)	—
$/M tokens	—
J/token	—
Power avg (W)	11.51
Power peak (W)	40.50
WER mean	0.0700
J / audio s	32.33

All metrics

audio_path_resolved_count	5.00
energy_joules_total	638
joules_per_audio_second	32.33
n_ok	5.00
n_samples	5.00
ok_rate	1.00
power_avg_w	11.51
power_peak_w	40.50
total_audio_duration_s	19.73
total_p50_ms	653
wer_mean	0.0700
wer_p50	0.0000
wer_p95	0.2200

Provenance

Model revision	`unknown00`
Provider	whisper-http
Hardware fingerprint	`7e8631bf6bd81c9152b8f2ddd589eb310f09c65f8fc19e6730aa84fa6ae94d33`
Dataset	librispeech-clean-mini · `cff1fdb61fe89ecdd453b7bbcc7850160645af4bc819dde51cd8dfcdf9c4eb33`
Timestamp	2026-05-25T16:25:18.052774+00:00
Envelope JSON	1cd8f74bac26.json

Verify this result

bench verify /bench/leaderboard/envelopes/1cd8f74bac26.json

bench verify re-downloads this envelope, recomputes the canonical content hash, and validates the Sigstore signature against the embedded certificate + Rekor entry.