File and tensor details
Sizes describe the stored artifacts. Each row describes one package or tensor file; alternative checkpoints and repeated exports are kept separate. Tensor-element counts include every stored array, which can include buffers, fitted parameters or diagnostic bases. They are not asserted to be a complete speech model's parameter count. Core ML input/output dtypes describe the interface; internal compute and weight precision may differ. A parseable specification does not establish runtime compatibility.
Machine-readable details, including tensor names and shapes.
Core ML packages
| Package | Stored size | Input → output dtypes | Specification |
|---|---|---|---|
| models/baseline-fp32.mlpackage | 206.46 MiB | FLOAT32 → FLOAT32 | parseable |
| models/baseline-fp16.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/mixed-fp32-convolution.mlpackage | 206.44 MiB | FLOAT32 → FLOAT32 | parseable |
| models/mixed-fp32-snake-residual.mlpackage | 103.33 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate1-affine.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate2-response.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate3-roi.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate4-spectral.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate4-shape.mlpackage | 103.28 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate5-polyphase.mlpackage | 107.78 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate5-channel-affine.mlpackage | 107.78 MiB | FLOAT32 → FLOAT32 | parseable |
| models/candidate6-response.mlpackage | 107.78 MiB | FLOAT32 → FLOAT32 | parseable |