{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "name": "agent-omni-multimodal — audio-speech",
  "dateModified": "2026-06-12T01:05:59.820Z",
  "asr_wer_th_pct": 2.1,
  "asr_wer_en_pct": 1.4,
  "tts_voices": 412,
  "langs": 142,
  "real_time_factor": 0.18,
  "diarization_der_pct": 3.2,
  "music_understanding": true
}