Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | Edge0Edge0/Audio8-ASR-0.1BRemove × |
|---|---|
| What’s different | 0.324B parameters · 7 languages · Encoder: Qwen3-ASR audio encoder · Decoder: 8-layer Qwen-style causal LM |
| Date | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | |
| Listed rate | See provider quotes |
| Provider endpoints | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 11% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 12.53% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 8.48% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 2.71% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 6.6% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 3.73% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 14.97% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 6.18% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 4.39% WER ↗Edge0/Audio8-ASR-0.1BLeaderboard entry |
Specifications | |
| Context window | — |
| Max output | — |
| Parameters | 0.324B |
| Audio input | Supported |
| Transcription | Supported |