Instructions to use argmaxinc/whisperkit-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use argmaxinc/whisperkit-pro with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- Notebooks
- Google Colab
- Kaggle
File size: 2,559 Bytes
e8f351b | 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 | [
{
"metadataOutputVersion" : "3.0",
"storagePrecision" : "Float16",
"outputSchema" : [
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 768 × 1 × 1500)",
"shortDescription" : "",
"shape" : "[1, 768, 1, 1500]",
"name" : "encoder_output_embeds",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 12 × 768 × 1 × 1536)",
"shortDescription" : "",
"shape" : "[12, 768, 1, 1536]",
"name" : "encoder_attn_key_cache",
"type" : "MultiArray"
},
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 12 × 768 × 1 × 1536)",
"shortDescription" : "",
"shape" : "[12, 768, 1, 1536]",
"name" : "encoder_attn_value_cache",
"type" : "MultiArray"
}
],
"modelParameters" : [
],
"specificationVersion" : 9,
"mlProgramOperationTypeHistogram" : {
"Pad" : 2,
"Ios18.batchNorm" : 25,
"Ios18.conv" : 98,
"Ios18.gelu" : 14,
"Ios18.concat" : 158,
"Ios16.einsum" : 1152,
"Ios18.add" : 25,
"Ios18.softmax" : 576,
"Ios18.sliceByIndex" : 1008,
"Ios18.layerNorm" : 25,
"Ios18.transpose" : 12,
"Ios18.mul" : 576
},
"computePrecision" : "Mixed (Float16, Int32)",
"isUpdatable" : "0",
"stateSchema" : [
],
"availability" : {
"macOS" : "15.0",
"tvOS" : "18.0",
"visionOS" : "2.0",
"watchOS" : "11.0",
"iOS" : "18.0",
"macCatalyst" : "18.0"
},
"modelType" : {
"name" : "MLModelType_mlProgram"
},
"userDefinedMetadata" : {
"com.github.apple.coremltools.source_dialect" : "TorchScript",
"com.github.apple.coremltools.source" : "torch==2.5.1",
"com.github.apple.coremltools.version" : "8.0"
},
"inputSchema" : [
{
"hasShapeFlexibility" : "0",
"isOptional" : "0",
"dataType" : "Float16",
"formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
"shortDescription" : "",
"shape" : "[1, 80, 1, 3000]",
"name" : "melspectrogram_features",
"type" : "MultiArray"
}
],
"generatedClassName" : "AudioEncoderStateful",
"method" : "predict"
}
] |