al8n's picture
fp16-safe conversion: fused x-logsumexp(x) tail; encoder weights byte-identical to upstream pin
a144c29 verified
Raw
History Blame Contribute Delete
2.31 kB
[
{
"metadataOutputVersion" : "3.0",
"shortDescription" : "wav2vec2-base-960h forced aligner, epsilon-safe (reduce_log_sum_exp->sub tail)",
"outputSchema" : [
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float32",
"formattedType" : "MultiArray (Float32 1 × 2999 × 29)",
"shortDescription" : "",
"shape" : "[1, 2999, 29]",
"name" : "emissions",
"type" : "MultiArray"
}
],
"storagePrecision" : "Float16",
"modelParameters" : [
],
"author" : "Phase-A reconversion: wav2vec2-base-960h aligner, stable fused log-softmax",
"specificationVersion" : 8,
"mlProgramOperationTypeHistogram" : {
"Ios17.mul" : 13,
"Ios17.sqrt" : 1,
"Ios17.square" : 1,
"Ios17.transpose" : 51,
"Ios17.sub" : 2,
"Ios17.linear" : 74,
"Ios17.conv" : 8,
"Ios17.matmul" : 24,
"Ios16.reduceLogSumExp" : 1,
"Ios17.add" : 27,
"Ios17.realDiv" : 1,
"Ios16.reduceMean" : 2,
"Ios17.sliceByIndex" : 1,
"Ios16.softmax" : 12,
"Ios16.gelu" : 20,
"Ios17.expandDims" : 1,
"Ios17.reshape" : 50,
"Ios17.cast" : 2,
"Ios17.layerNorm" : 26
},
"computePrecision" : "Mixed (Float16, Float32, Int32)",
"isUpdatable" : "0",
"stateSchema" : [
],
"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" : "Float32",
"formattedType" : "MultiArray (Float32 1 × 960000)",
"shortDescription" : "",
"shape" : "[1, 960000]",
"name" : "waveform",
"type" : "MultiArray"
}
],
"userDefinedMetadata" : {
"com.github.apple.coremltools.conversion_date" : "2026-07-16",
"com.github.apple.coremltools.source" : "torch==2.5.1",
"com.github.apple.coremltools.version" : "9.0",
"com.github.apple.coremltools.source_dialect" : "TorchScript"
},
"generatedClassName" : "base960h_aligner",
"method" : "predict"
}
]