{ "model": "pingo-ptbr", "benchmark": "MiniMax pt (100 sentences per voice), Qwen3-ASR, open-tts-leaderboard normalizer", "noise_note": "WER moves by about +/-0.2 points between runs; differences below that are noise", "results": [ { "model": "pingo-ptbr (width 64, quantized, with duration limit)", "weights_mb": 0.871, "wer_percent": { "F_s4": 0.86, "M_sm4": 0.81 }, "note": "measured after the duration limit of docs/EXPERIMENTS.md section 9; without the limit: F_s4 0.95, M_sm4 1.00" }, { "model": "pingo-ptbr-w96 (width 96, quantized)", "weights_mb": 1.086, "wer_percent": { "F_s4": 0.81, "M_sm4": 1.0 } }, { "model": "pivo-ptbr float32 (measured with MLX)", "weights_mb": 5.61, "wer_percent": { "F_s4": 0.95, "M_sm4": 0.95 } }, { "model": "pivo-ptbr float32 (ONNX, published)", "weights_mb": 5.8, "wer_percent": { "F_s4": 0.95, "M_sm4": 0.81 } }, { "model": "tiny-voca-ptbr", "wer_percent": { "F_s4": 0.9, "M_sm4": 0.86 } } ], "quantization_study": "see docs/EXPERIMENTS.md", "training_validation_loss": { "2000": 0.2028, "6000": 0.1841, "10000": 0.1789, "20000": 0.1736, "30000": 0.1707, "40000": 0.1699 } }