{
 "model": "Dynamic ASR Pocket",
 "architecture": "omniASR_CTC_300M_v2 student distilled from a 1B Dynamic ASR teacher (omniASR_CTC_1B_v2 fine-tune)",
 "checkpoint": "P2, step 2500",
 "decoding": "greedy CTC, no language model",
 "input": "16 kHz mono float32",
 "scoring": "CER after: NFC, lowercase, punctuation and apostrophes to spaces, English number words to digits, dot-below variants unified, Igbo tone marks stripped from both sides (Yoruba tone marks kept)",
 "eval_sets": {
  "gdev": "general dev set (WAXAL validation + OpenSLR-70; 187 clips, 1269 s; eng/hau/ibo/pcm/yor). Used for checkpoint selection, so it is a dev set, not a test set.",
  "real_codeswitch": "held-out real code-switched speech test set (94 clips, 758 s); never used for training or selection"
 },
 "results": {
  "pocket_int8_onnx": {
   "gdev_cer": {
    "eng": 0.0571,
    "hau": 0.0522,
    "ibo": 0.0595,
    "pcm": 0.0963,
    "yor": 0.1359,
    "mean": 0.0802
   },
   "real_codeswitch_cer": 0.1558,
   "real_codeswitch_wer": 0.4311,
   "real_codeswitch_english_word_recall": 0.3009
  },
  "pocket_fp32_onnx": {
   "gdev_cer": {
    "eng": 0.0571,
    "hau": 0.0514,
    "ibo": 0.0595,
    "pcm": 0.0925,
    "yor": 0.135,
    "mean": 0.0791
   },
   "real_codeswitch_cer": 0.1558,
   "real_codeswitch_wer": 0.4333,
   "real_codeswitch_english_word_recall": 0.3009
  },
  "pocket_pytorch_fp32": {
   "gdev_cer": {
    "eng": 0.0571,
    "hau": 0.0514,
    "ibo": 0.0595,
    "pcm": 0.0925,
    "yor": 0.135,
    "mean": 0.0791
   },
   "real_codeswitch_cer": 0.1558,
   "real_codeswitch_wer": 0.4333,
   "real_codeswitch_english_word_recall": 0.3009
  },
  "teacher_1b_greedy": {
   "gdev_cer": {
    "eng": 0.0294,
    "hau": 0.0489,
    "ibo": 0.0598,
    "pcm": 0.0823,
    "yor": 0.1288,
    "mean": 0.0698
   },
   "real_codeswitch_cer": 0.1375,
   "real_codeswitch_wer": 0.3968,
   "real_codeswitch_english_word_recall": 0.4248
  }
 },
 "sizes_bytes": {
  "model_int8.onnx": 366630967,
  "model_fp32.onnx": 1304478206,
  "model.pt": 1304038762
 },
 "cpu_benchmark": {
  "cpu": "Intel Xeon Platinum 8480+",
  "batch": 1,
  "clips": 20,
  "audio_s": 110.1,
  "runs": [
   {
    "model": "pocket_int8.onnx",
    "threads": 4,
    "rtf": 0.0706,
    "ms_median": 357.7,
    "ms_p90": 509.3,
    "peak_rss_mb": 939.1,
    "load_s": 1.02
   },
   {
    "model": "pocket_int8.onnx",
    "threads": 2,
    "rtf": 0.133,
    "ms_median": 693.8,
    "ms_p90": 947.1,
    "peak_rss_mb": 935.2,
    "load_s": 1.0
   },
   {
    "model": "pocket_int8.onnx",
    "threads": 1,
    "rtf": 0.139,
    "ms_median": 708.1,
    "ms_p90": 995.2,
    "peak_rss_mb": 935.2,
    "load_s": 0.92
   },
   {
    "model": "pocket_fp32.onnx",
    "threads": 4,
    "rtf": 0.1857,
    "ms_median": 952.1,
    "ms_p90": 1294.9,
    "peak_rss_mb": 2287.3,
    "load_s": 3.21
   }
  ]
 },
 "notes": [
  "The 1B teacher is an internal checkpoint used for distillation; it is not one of the model files in this repository.",
  "English is the largest gap between Pocket and the teacher."
 ],
 "training_data": "licensed real speech (same sources as the 1B models), real-voice splice code-switch clips built from that licensed speech, and an oversample of 0.9 h of real code-switched training clips; no synthetic TTS audio; no African Voices data",
 "distillation": "CTC loss on references + KL divergence to the 1B teacher's per-frame distribution; CNN feature encoder frozen"
}