KModel loads mismatched checkpoints silently via strict=False

Summary

KModel loads checkpoint state dicts with a silent strict=False fallback. A finetuned checkpoint saved in the newer torch.nn.utils.parametrizations.weight_norm format uses keys such as *.parametrizations.weight.original0 / *.parametrizations.weight.original1, instead of the *.weight_g / *.weight_v keys the model's modules expect. Because loading is not strict, such a checkpoint "loads successfully" but leaves every weight-norm layer at its random initialization. The result is pure noise instead of speech, with no error and no warning. This affects at least one publicly available finetune family for a non-English language (e.g. the "kikiri-tts" checkpoints).

Environment

• kokoro 0.7.16
• PyTorch 2.x
• Python 3.13
• macOS arm64 (Apple Silicon, M1 Max)

Reproduction

1. Load such a checkpoint directly into KModel — output is noise, with no error or warning raised.
2. Remap the keys (original0 -> weight_g, original1 -> weight_v) and call load_state_dict(strict=True) per component — output is then correct speech.

Expected vs. Actual

• Expected: a checkpoint whose keys don't cover the model's parameters should fail loudly, or at least warn, rather than "succeed" with randomly-initialized layers.
• Actual: the silent strict=False fallback accepts partial/mismatched checkpoints with no diagnostic, producing a model that runs but only emits noise.

Suggestion

Check key coverage when loading and fail loudly (or warn clearly) on incomplete coverage, or expose a strict option to callers. Optionally, detect and remap the parametrizations.weight.* naming directly, since it is a standard PyTorch parametrization format.