File size: 3,435 Bytes
c5dd26f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | [
{
"metadataOutputVersion" : "3.0",
"shortDescription" : "emotion2vec_plus_base speech emotion recognition (9 classes). Input: 16 kHz mono float32 waveform, 0.5-10 s.",
"outputSchema" : [
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float32",
"formattedType" : "MultiArray (Float32 1 × 9)",
"shortDescription" : "Softmax probabilities [1, 9]: 0=angry, 1=disgusted, 2=fearful, 3=happy, 4=neutral, 5=other, 6=sad, 7=surprised, 8=unknown",
"shape" : "[1, 9]",
"name" : "probs",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float32",
"formattedType" : "MultiArray (Float32 1 × 9)",
"shortDescription" : "Pre-softmax logits [1, 9]",
"shape" : "[1, 9]",
"name" : "logits",
"type" : "MultiArray"
}
],
"storagePrecision" : "Mixed (Float16, Float32, Int8)",
"modelParameters" : [
],
"author" : "emotion2vec (Ma et al.), converted from FunASR checkpoint emotion2vec\/emotion2vec_plus_base",
"specificationVersion" : 9,
"license" : "See emotion2vec\/emotion2vec_plus_base model card",
"mlProgramOperationTypeHistogram" : {
"Ios18.expandDims" : 7,
"Ios18.mul" : 18,
"Ios18.softmax" : 13,
"Ios18.rsqrt" : 1,
"Ios18.matmul" : 24,
"Ios16.reduceMean" : 3,
"Ios18.greaterEqual" : 1,
"Ios18.add" : 38,
"Ios18.layerNorm" : 38,
"Ios16.fillLike" : 1,
"Ios18.reshape" : 24,
"Ios18.linear" : 50,
"Ios18.conv" : 12,
"Ios18.gelu" : 24,
"Ios18.sub" : 3,
"Ios18.concat" : 1,
"Ios18.cast" : 8,
"Ios18.transpose" : 47,
"Ios18.abs" : 1,
"Ios18.sliceByIndex" : 39,
"Ios16.cumsum" : 1,
"Ios18.constexprBlockwiseShiftScale" : 63
},
"computePrecision" : "Mixed (Float16, Float32, Int32)",
"stateSchema" : [
],
"isUpdatable" : "0",
"availability" : {
"macOS" : "15.0",
"tvOS" : "18.0",
"visionOS" : "2.0",
"watchOS" : "11.0",
"iOS" : "18.0",
"macCatalyst" : "18.0"
},
"modelType" : {
"name" : "MLModelType_mlProgram"
},
"inputSchema" : [
{
"dataType" : "Float32",
"hasShapeFlexibility" : "1",
"isOptional" : "0",
"shapeFlexibility" : "1 × 8000...160000",
"shapeRange" : "[[1, 1], [8000, 160000]]",
"formattedType" : "MultiArray (Float32 1 × 48000)",
"type" : "MultiArray",
"shape" : "[1, 48000]",
"name" : "audio",
"shortDescription" : "Raw mono waveform at 16 kHz, float32 in [-1, 1], shape [1, N], 8000 <= N <= 160000. Normalised internally."
}
],
"userDefinedMetadata" : {
"labels" : "angry,disgusted,fearful,happy,neutral,other,sad,surprised,unknown",
"labels_original" : "生气\/angry,厌恶\/disgusted,恐惧\/fearful,开心\/happy,中立\/neutral,其他\/other,难过\/sad,吃惊\/surprised,<unk>",
"com.github.apple.coremltools.conversion_date" : "2026-10-06",
"com.github.apple.coremltools.version" : "9.0",
"com.github.apple.coremltools.source" : "torch==2.7.0",
"sample_rate" : "16000",
"com.github.apple.coremltools.source_dialect" : "TorchScript"
},
"generatedClassName" : "Emotion2Vec8bit",
"method" : "predict"
}
] |