Use isolates to run inference

[luiscib3r]

When inference is running in models that take a long time. The UI it freezes/locked because everything runs on a single thread.

Consider the possibility of implementing Isolate.spawn to run the model. The developer could do this externally, but it would be better if this process is handled within the package. The run method could return the execution status in a stream [loading, done]

[luiscib3r]

I solved this and have added to PR #49.

final interpreter = Interpreter.fromAssets('assets/yourmodel.tflite');
final isolateInterpreter = IsolateInterpreter(address: interpreter.address);

Now interpreter continues working in the same way. But in isolateInterpreter the methods isolateInterpreter.run and isolateInterpreter.runForMultipleInputs are asynchronous and internally what they do is use an isolate to execute the inference, this way the ui does not freeze. You can also use isolateInterpreter.state and isolateInterpreter.stateChanges (a Stream) to know the state of the interpreter (idle or loading).