Automatic Speech Recognition
Core ML
NeMo
apple-neural-engine
on-device
ios
macos
speech
audio
automatic-speech-translation
canary
fastconformer
kv-cache
fp16
Instructions to use smdesai/canary-1b-v2-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use smdesai/canary-1b-v2-coreml with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("smdesai/canary-1b-v2-coreml") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
| [ | |
| { | |
| "metadataOutputVersion" : "3.0", | |
| "shortDescription" : "Canary-1b-v2 FastConformer encoder (32L, d=1024, ss=8)", | |
| "outputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float32", | |
| "formattedType" : "MultiArray (Float32 1 × 188 × 1024)", | |
| "shortDescription" : "", | |
| "shape" : "[1, 188, 1024]", | |
| "name" : "enc_states", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Int32", | |
| "formattedType" : "MultiArray (Int32 1)", | |
| "shortDescription" : "", | |
| "shape" : "[1]", | |
| "name" : "encoder_length", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "storagePrecision" : "Float16", | |
| "modelParameters" : [ | |
| ], | |
| "specificationVersion" : 8, | |
| "mlProgramOperationTypeHistogram" : { | |
| "Ios17.floor" : 3, | |
| "Ios17.logicalAnd" : 2, | |
| "Ios17.reshape" : 193, | |
| "Ios16.softmax" : 32, | |
| "Ios17.matmul" : 96, | |
| "Ios17.transpose" : 227, | |
| "Split" : 32, | |
| "Select" : 96, | |
| "Ios17.expandDims" : 5, | |
| "Ios17.add" : 230, | |
| "Tile" : 1, | |
| "Ios17.sliceByIndex" : 64, | |
| "Ios16.sigmoid" : 32, | |
| "Pad" : 64, | |
| "Ios17.logicalNot" : 2, | |
| "Ios17.layerNorm" : 160, | |
| "Ios16.silu" : 96, | |
| "Ios17.less" : 1, | |
| "Ios17.conv" : 101, | |
| "Ios16.relu" : 3, | |
| "Ios17.cast" : 4, | |
| "Ios17.linear" : 257, | |
| "Ios17.mul" : 131 | |
| }, | |
| "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 × 128 × 1501)", | |
| "shortDescription" : "", | |
| "shape" : "[1, 128, 1501]", | |
| "name" : "mel", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Int32", | |
| "formattedType" : "MultiArray (Int32 1)", | |
| "shortDescription" : "", | |
| "shape" : "[1]", | |
| "name" : "mel_length", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "userDefinedMetadata" : { | |
| "com.github.apple.coremltools.conversion_date" : "2026-06-25", | |
| "com.github.apple.coremltools.source" : "torch==2.7.0", | |
| "com.github.apple.coremltools.version" : "9.0b1", | |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" | |
| }, | |
| "generatedClassName" : "canary_encoder", | |
| "method" : "predict" | |
| } | |
| ] |