Training sound classifier on device

I'm trying to train a CoreML sound classifier on device, on iOS, and I have been struggling to find learning resources on the topic. The sound classifier is used to determine whether a snippet of music is similar to a collection of other songs. Hence the output of the classifier is just a label of either "match" / "no match".

It is so simple to train with the CreateML app workflow. I am simply trying to get the same kind of training on device in iOS, but as far as I know (please correct me if I'm wrong) iOS doesn't support createML.

I have been trying to adapt code from various source to get this to work in an iOS playground. I can only find resources on training image classifiers, these two have been the most helpful (1, 2).

Please see the code that I have come up with so far below.

import UIKit
import CoreML

func convertDataToArray<T>(count: Int, data: Data) -> [T] {
    let array = data.withUnsafeBytes { (pointer: UnsafePointer<T>) -> [T] in
        let buffer = UnsafeBufferPointer(start: pointer, count: count / MemoryLayout<Float32>.size)
        return Array<T>(buffer)
    }
    return array
}

// Get files (names and paths) in directory
public func getAllFilesInDirectory(bundle: Bundle, directory: String, extensionWanted: String) -> (names: [String], paths: [URL]) {
    let cachesURL = URL(fileURLWithPath: "/Users/...../Playgrounds/MLPlayground.playground/Resources")
    let directoryURL = cachesURL.appendingPathComponent(directory)

    do {
        try FileManager.default.createDirectory(atPath: directoryURL.relativePath, withIntermediateDirectories: true)
        
        // Get the directory contents urls (including subfolders urls)
        let directoryContents = try FileManager.default.contentsOfDirectory(at: directoryURL, includingPropertiesForKeys: nil, options: [])

        // Filter the directory contents
        let filesPath = directoryContents.filter{ $0.pathExtension == extensionWanted }
        let fileNames = filesPath.map{ $0.deletingPathExtension().lastPathComponent }

        return (names: fileNames, paths: filesPath);

    } catch {
        print("Failed to fetch contents of directory: \(error.localizedDescription)")
    }

    return (names: [], paths: [])
}


let bundle = Bundle.main
var featureProviders = [MLFeatureProvider]()

let matchDir = getAllFilesInDirectory(bundle: bundle, directory: "Match", extensionWanted: "m4a")
let noMatchDir = getAllFilesInDirectory(bundle: bundle, directory: "No Match", extensionWanted: "m4a")


// I have ommited the full path directories for Stack Overflow
try! MLModel.compileModel(at: URL(fileURLWithPath: "/Users/...../Playgrounds/MLPlayground.playground/Resources/UpdateableML.mlmodel"))

let modelDir = URL(fileURLWithPath: "/Users/....../Playgrounds/MLPlayground.playground/Resources/UpdateableML.mlmodel")
let outputDir = URL(fileURLWithPath: "/Users/....../Playgrounds/MLPlayground.playground/Resources/Output/outputmodel.mlmodel")




func getFeatureProvider(forLabel: String, directory: URL) {
    let data = try! Data(contentsOf: directory.appendingPathComponent("\(forLabel).m4a"))
    
    // MultiArray (Float32 15600)
    let mlInputData = try! MLMultiArray(shape: [15600], dataType: .float32)
    
    let songDataArray: [Float32] = convertDataToArray(count: data.count, data: data)
    let count = songDataArray.count

    for i in 0..<mlInputData.count {
        mlInputData[i] = NSNumber(value: songDataArray[i])
    }
    
    let soundValue = MLFeatureValue(multiArray: mlInputData)
    let outputValue = MLFeatureValue(string: forLabel)
    
    let dataPointFeatures: [String: MLFeatureValue] = ["audioSamples": soundValue, "classLabel": outputValue]
    
    if let provider = try? MLDictionaryFeatureProvider(dictionary: dataPointFeatures) {
        featureProviders.append(provider)
    } else {
        print("Failed to get provider")
    }
}


// Get features
for s in matchDir.names {
    getFeatureProvider(forLabel: s, directory: matchDir.paths.first!.deletingLastPathComponent())
}
for s in noMatchDir.names {
    getFeatureProvider(forLabel: s, directory: noMatchDir.paths.first!.deletingLastPathComponent())
}



var batchProvider = MLArrayBatchProvider(array: featureProviders)




func updateModel(at url: URL, with trainingData: MLBatchProvider, completionHandler: @escaping (MLUpdateContext) -> Void) {
    let updateTask = try! MLUpdateTask(
        forModelAt: url,
        trainingData: trainingData,
        configuration: nil,
        completionHandler: completionHandler
    )
    updateTask.resume()
}



func saveUpdatedModel(_ updateContext: MLUpdateContext) {
    let updatedModel = updateContext.model
    let fileManager = FileManager.default
    do {
        try fileManager.createDirectory(
            at: outputDir,
            withIntermediateDirectories: true,
            attributes: nil)
        
        try updatedModel.write(to: outputDir)
        print("Updated model saved to:\n\t\(outputDir)")
    } catch let error {
        print("Could not save updated model to the file system: \(error)")
        return
    }
}



func updateWith(trainingData: MLBatchProvider, completionHandler: @escaping () -> Void) {
    updateModel(at: modelDir, with: trainingData) { context in
        print("Update Complete")
        saveUpdatedModel(context)
        completionHandler()
    }
}


updateWith(trainingData: batchProvider, completionHandler: {
    print("Final Complete")
})

I have two issues at the moment:

• I receive the following error from the MLUpdateTask at function 'updateModel':

Fatal error: 'try!' expression unexpectedly raised an error: Error Domain=com.apple.CoreML Code=0 "Unable to load model at file:///Users/....../Playgrounds/CuratorMLPlayground.playground/Resources/UpdateableML.mlmodel with error: Error opening file stream: /Users/....../Playgrounds/CuratorMLPlayground.playground/Resources/UpdateableML.mlmodel/coremldata.bin: unspecified iostream_category error"

• I don't know if I am fetching the audio data correctly at the function 'getFeatureProvider' because the size of 'songDataArray' is roughly 260000 and the shape of the model/'mlInputData' is 15600 ? Could someone please explain this to me.

UPDATE: I've copied this over to my actual iOS app project. I am now getting the following error in place of the one above.

Fatal error: 'try!' expression unexpectedly raised an error: Error Domain=com.apple.CoreML Code=0 "Invalid URL for .mlmodel." UserInfo={NSLocalizedDescription=Invalid URL for .mlmodel.}:

However, I am almost certain the URL is correctly pointing to the mlmodel