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 cross-attention K\/V precompute (per-window, 8L)", | |
| "outputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float32", | |
| "formattedType" : "MultiArray (Float32 8 × 1 × 8 × 188 × 128)", | |
| "shortDescription" : "", | |
| "shape" : "[8, 1, 8, 188, 128]", | |
| "name" : "enc_k", | |
| "type" : "MultiArray" | |
| }, | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float32", | |
| "formattedType" : "MultiArray (Float32 8 × 1 × 8 × 188 × 128)", | |
| "shortDescription" : "", | |
| "shape" : "[8, 1, 8, 188, 128]", | |
| "name" : "enc_v", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "storagePrecision" : "Float16", | |
| "modelParameters" : [ | |
| ], | |
| "specificationVersion" : 9, | |
| "mlProgramOperationTypeHistogram" : { | |
| "Ios18.linear" : 16, | |
| "Ios18.transpose" : 16, | |
| "Stack" : 2, | |
| "Ios18.cast" : 3, | |
| "Ios18.reshape" : 16, | |
| "Ios18.mul" : 8 | |
| }, | |
| "computePrecision" : "Mixed (Float16, Float32, 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" | |
| }, | |
| "inputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float32", | |
| "formattedType" : "MultiArray (Float32 1 × 188 × 1024)", | |
| "shortDescription" : "", | |
| "shape" : "[1, 188, 1024]", | |
| "name" : "enc_states", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "userDefinedMetadata" : { | |
| "com.github.apple.coremltools.conversion_date" : "2026-07-01", | |
| "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_cross_kv", | |
| "method" : "predict" | |
| } | |
| ] |