{
  "model": "Fasih-TTS-V1",
  "base_model": "coqui/XTTS-v2",
  "language": "ar",
  "variant": "MSA / Fusha, single professional male voice",
  "evaluation": {
    "metric": "CER (%)",
    "asr_judge": "openai/whisper-large-v3 (via faster-whisper)",
    "normalization": "diacritics-stripped + orthography-normalized (both hyp and ref)",
    "sets": {
      "varied_msa": {"clips": 8, "mean_cer": 1.3, "worst_cer": 2.2},
      "same_sentence_x4": {"clips": 4, "mean_cer": 2.0, "worst_cer": 2.0},
      "long_text_chunked": {"clips": 2, "mean_cer": 0.8, "worst_cer": 0.9},
      "hard_stress": {"clips": 6, "mean_cer": 2.1, "worst_cer": 8.2},
      "human_originals_floor": {"clips": 8, "mean_cer": 1.8, "worst_cer": 4.8}
    },
    "summary": {
      "tts_mean_cer": 1.3,
      "human_floor_mean_cer": 1.8,
      "gap_points": -0.5,
      "instability_events": 0
    }
  },
  "efficiency": {
    "gpu": "1x NVIDIA RTX 2080 Ti (Turing, FP32)",
    "rtf": 0.60,
    "streaming_time_to_first_audio_ms": 675,
    "output_sample_rate_hz": 24000
  },
  "training": {
    "data_clips": 1297,
    "data_hours": 2.4,
    "precision": "fp32",
    "best_val_loss": 2.622,
    "diacritization": "CATT encoder-decoder"
  },
  "silma_benchmark": {
    "source": "silma-ai/opensource-arabic-tts-benchmark",
    "split": "msa",
    "sentences": 10,
    "judges": ["openai/whisper-large-v3", "nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0", "UTMOS22 (naturalness)"],
    "note": "WER=intelligibility (lower better); UTMOS=naturalness proxy (higher better); SILMA's own benchmark is human-auditory.",
    "results": [
      {"model": "Fasih-TTS-V1 (ours)", "wer_whisper": 6.5, "wer_nemo": 2.5, "utmos": 3.16},
      {"model": "xtts (base)", "wer_whisper": 10.3, "wer_nemo": 2.5, "utmos": 2.99},
      {"model": "chatterbox", "wer_whisper": 12.8, "wer_nemo": 5.4, "utmos": 3.20},
      {"model": "silma_tts", "wer_whisper": 11.1, "wer_nemo": 5.8, "utmos": 3.15},
      {"model": "omnivoice", "wer_whisper": 15.3, "wer_nemo": 7.3, "utmos": 3.62},
      {"model": "habibi_specialized", "wer_whisper": 21.9, "wer_nemo": 23.3, "utmos": 2.33}
    ],
    "summary": "Fasih is top-tier intelligibility (best-or-tied WER across both ASR judges); mid-pack naturalness (UTMOS #3)."
  }
}