| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Geolocation-Aware Robust Spoken Language Identification | ✓ Link | 97.7 | GeoLID (Combined) (extra data) | 2025-08-23 |
| Scaling Speech Technology to 1,000+ Languages | ✓ Link | 97.5 | MMS-126 (extra data) | 2023-05-27 |
| OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning | ✓ Link | 95.6 | OWSM v4 medium (extra data) | 2025-01-16 |
| A Compact End-to-End Model with Local and Global Context for Spoken Language Identification | ✓ Link | 88.2 | TitaNet-LID-3x5x1024 (extra data) | 2022-10-27 |
| OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification | ✓ Link | 87.6 | OWSM-CTC Medium (extra data) | 2024-02-23 |