| [ |
| { |
| "shortDescription" : "Parakeet Ultra prediction network (RNN-T decoder), one step with explicit LSTM state", |
| "metadataOutputVersion" : "3.0", |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 1 × 640 × 1)", |
| "shortDescription" : "", |
| "shape" : "[1, 640, 1]", |
| "name" : "decoder", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 2 × 1 × 640)", |
| "shortDescription" : "", |
| "shape" : "[2, 1, 640]", |
| "name" : "h_out", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 2 × 1 × 640)", |
| "shortDescription" : "", |
| "shape" : "[2, 1, 640]", |
| "name" : "c_out", |
| "type" : "MultiArray" |
| } |
| ], |
| "version" : "1", |
| "modelParameters" : [ |
|
|
| ], |
| "author" : "AnySpeechRecognizer", |
| "specificationVersion" : 8, |
| "storagePrecision" : "Float16", |
| "license" : "CC-BY-4.0. Parakeet Ultra by Moondream (https:\/\/huggingface.co\/moondream\/parakeet-ultra), a post-trained version of Parakeet TDT 0.6B v3 by NVIDIA (https:\/\/huggingface.co\/nvidia\/parakeet-tdt-0.6b-v3); both licensed under CC BY 4.0 (https:\/\/creativecommons.org\/licenses\/by\/4.0\/). Converted to Core ML for AnySpeechRecognizer: the model is split into encoder, prediction network, and joint decision components, weights are stored in float16, and encoder weights are quantized to int8.", |
| "mlProgramOperationTypeHistogram" : { |
| "Select" : 1, |
| "Ios17.squeeze" : 4, |
| "Ios17.gather" : 1, |
| "Ios17.cast" : 8, |
| "Ios17.lstm" : 2, |
| "Split" : 2, |
| "Ios17.add" : 1, |
| "Ios17.transpose" : 2, |
| "Ios17.greaterEqual" : 1, |
| "Identity" : 1, |
| "Stack" : 2 |
| }, |
| "computePrecision" : "Mixed (Float16, Float32, Int16, Int32)", |
| "stateSchema" : [ |
|
|
| ], |
| "isUpdatable" : "0", |
| "availability" : { |
| "macOS" : "14.0", |
| "tvOS" : "17.0", |
| "visionOS" : "1.0", |
| "watchOS" : "10.0", |
| "iOS" : "17.0", |
| "macCatalyst" : "17.0" |
| }, |
| "modelType" : { |
| "name" : "MLModelType_mlProgram" |
| }, |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1 × 1)", |
| "shortDescription" : "", |
| "shape" : "[1, 1]", |
| "name" : "targets", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "target_length", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 2 × 1 × 640)", |
| "shortDescription" : "", |
| "shape" : "[2, 1, 640]", |
| "name" : "h_in", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 2 × 1 × 640)", |
| "shortDescription" : "", |
| "shape" : "[2, 1, 640]", |
| "name" : "c_in", |
| "type" : "MultiArray" |
| } |
| ], |
| "userDefinedMetadata" : { |
| "com.github.apple.coremltools.conversion_date" : "2026-10-13", |
| "source_checkpoints" : "nvidia\/parakeet-tdt-0.6b-v3@541d1f99c6b0c3cd0b11a95167540bb8edefd82b, moondream\/parakeet-ultra@73175eb7aeb0d82f1e2a6b53b3aabc10a90bcd0b", |
| "com.github.apple.coremltools.source" : "torch==2.7.0", |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" |
| }, |
| "generatedClassName" : "Decoder", |
| "method" : "predict" |
| } |
| ] |
