Speech Recognition on Tedlium
3.56WERLFM2-Audio-1.5B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LFM2-Audio-1.5B# Total Params=1.5B2025.11 | 3.56 | — | |
| Whisper-large-v3-turbo# Total Params=1.5B2025.11 | 3.57 | — | |
| Qwen3-ASR-0.6BParameters=0.6B2026.01 | 3.85 | — | |
| WhisperBackbone=Large V2, Evaluation Protocol=Zero-shot2022.12 | 4 | 61.9 | |
| Qwen3-ASR-1.7BParameters=1.7B2026.01 | 4.5 | — | |
| Doubao-ASR2026.01 | 4.91 | — | |
| Qwen2.5-Omni-3B# Total Params=5B2025.11 | 5.08 | — | |
| Gemini-2.5-Pro2026.01 | 6.15 | — | |
| Whisper-large-v32026.01 | 6.84 | — | |
| GPT-4o-Transcribe2026.01 | 7.69 | — | |
| wav2vec 2.0Backbone=Large, Language Model=None2022.12 | 10.5 | — |