Model card
Cohere Transcribe (Mar 2026).
CohereSpeech-to-text2B paramsTransformer ASROpen source
Lowest LibriSpeech test-clean WER (1.25%); 5.42% mean WER, #2 overall.
§ 02 · Benchmarks
No recorded benchmark results yet.
This model is in the registry but doesn’t have any benchmark_results rows yet. If you have a score, submit it →
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 05 · Related models