Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | Edge0Edge0/ARK-ASR-3BRemove × | Briaremove_background_guidedRemove × |
|---|---|---|
| What’s different | 3.75B parameters · 19 languages · Encoder: Whisper · Decoder: Qwen2 | Prompt-guided background removal by Bria: tell it what to keep or what to remove and get a clean cutout with true transparency, at the original resolution with the original pixels untouched. Trained… |
| Date | Oct 17, 2026Discovered | Oct 14, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | See provider quotes |
| Provider endpoints | 0 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 7.89% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 8.07% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 6.94% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| LS Clean WER ↗English short-form; normalization unversioned | 1.04% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| LS Other WER ↗English short-form; normalization unversioned | 2.37% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| SPGISpeech WER ↗English short-form; normalization unversioned | 2.46% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| URGENT2024 WER ↗English short-form; normalization unversioned | 13.29% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3.48% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 3.55% WER ↗Edge0/ARK-ASR-3BLeaderboard entry | Not reported |
Specifications | ||
| Context window | — | — |
| Max output | — | — |
| Parameters | 3.75B | — |
| Audio input | Supported | Not reported |
| Transcription | Supported | Not reported |