meeting-assistant/MeetingAssistant/Transcription/SpeechRecognitionPipelineHostedService.cs

using MeetingAssistant.LaunchProfiles;

namespace MeetingAssistant.Transcription;

public sealed class SpeechRecognitionPipelineHostedService : IHostedService
{
    private readonly ISpeechRecognitionPipelineFactory pipelineFactory;
    private readonly ILaunchProfileOptionsProvider? launchProfiles;
    private readonly ILogger<SpeechRecognitionPipelineHostedService> logger;
    private CancellationTokenSource? startupCancellation;
    private Task? startupTask;
    private List<ISpeechRecognitionPipeline> startupPipelines = [];

    public SpeechRecognitionPipelineHostedService(
        ISpeechRecognitionPipelineFactory pipelineFactory,
        ILogger<SpeechRecognitionPipelineHostedService> logger)
        : this(pipelineFactory, null, logger)
    {
    }

    public SpeechRecognitionPipelineHostedService(
        ISpeechRecognitionPipelineFactory pipelineFactory,
        ILaunchProfileOptionsProvider? launchProfiles,
        ILogger<SpeechRecognitionPipelineHostedService> logger)
    {
        this.pipelineFactory = pipelineFactory;
        this.launchProfiles = launchProfiles;
        this.logger = logger;
    }

    public Task StartAsync(CancellationToken cancellationToken)
    {
        var cancellation = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
        var pipelines = CreateStartupPipelines();
        startupCancellation = cancellation;
        startupPipelines = pipelines;
        startupTask = Task.Run(
            () => WarmUpPipelinesAsync(pipelines, cancellation.Token),
            CancellationToken.None);
        return Task.CompletedTask;
    }

    public async Task StopAsync(CancellationToken cancellationToken)
    {
        var cancellation = startupCancellation;
        var task = startupTask;
        var pipelines = startupPipelines;
        if (cancellation is null || task is null)
        {
            return;
        }

        startupCancellation = null;
        startupTask = null;
        startupPipelines = [];
        await cancellation.CancelAsync();
        try
        {
            await task.WaitAsync(cancellationToken);
        }
        catch (OperationCanceledException)
        {
        }
        finally
        {
            foreach (var pipeline in pipelines)
            {
                await pipeline.DisposeAsync();
            }

            cancellation.Dispose();
        }
    }

    private List<ISpeechRecognitionPipeline> CreateStartupPipelines()
    {
        if (launchProfiles is null)
        {
            return [pipelineFactory.Create()];
        }

        return launchProfiles.GetProfiles()
            .Where(ShouldWarmUpProfile)
            .Select(profile => pipelineFactory.Create(profile.Name))
            .ToList();
    }

    private static bool ShouldWarmUpProfile(LaunchProfile profile)
    {
        return profile.Name.Equals(
                ConfigurationLaunchProfileOptionsProvider.DefaultProfileName,
                StringComparison.OrdinalIgnoreCase) ||
            profile.Options.Recording.TranscriptionProvider.Equals("funasr", StringComparison.OrdinalIgnoreCase);
    }

    private async Task WarmUpPipelinesAsync(
        IReadOnlyList<ISpeechRecognitionPipeline> pipelines,
        CancellationToken cancellationToken)
    {
        await Task.WhenAll(pipelines.Select(pipeline => WarmUpPipelineAsync(pipeline, cancellationToken)));
    }

    private async Task WarmUpPipelineAsync(
        ISpeechRecognitionPipeline pipeline,
        CancellationToken cancellationToken)
    {
        try
        {
            await pipeline.InitializeAsync(cancellationToken);
            await pipeline.WaitUntilReadyAsync(cancellationToken);
        }
        catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
        {
            logger.LogInformation("Speech recognition pipeline warm-up was cancelled during application shutdown");
        }
        catch (Exception exception)
        {
            logger.LogError(
                exception,
                "Speech recognition pipeline warm-up failed; recording can still start and recognition will retry when audio is processed");
        }
    }
}