769c63b005
All checks were successful
ci/woodpecker/push/woodpecker Pipeline was successful
- Add Domain interfaces: IMistralService, IVoskService, ITtsService - Add Configuration classes: VoskConfig, CoquiConfig - Add Application service: MistralService (text generation with Mistral) - Add Infrastructure services: VoskService (speech recognition), TtsService (TTS) - Add Presentation controllers: MistralController, SpeechController, TtsController - Fix MistralService to use correct IMistralConnector methods (CompleteAsync, ChatAsync) - Fix TtsController to use record constructor syntax - Fix TtsService Task.FromResult type specification - Fix Program.cs service registration and remove merge conflict markers - Update docs/features/ai-services.md with progress (Phases 0-4 complete) - Update docs/ROADMAP.md with AI Services status and test metrics (296 tests) Generated by Mistral Vibe. Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
57 lines
2.1 KiB
C#
57 lines
2.1 KiB
C#
namespace GermanApp.Domain.Interfaces;
|
|
|
|
/// <summary>
|
|
/// Domain interface for Vosk speech recognition service.
|
|
/// This is part of the Domain layer.
|
|
/// </summary>
|
|
public interface IVoskService
|
|
{
|
|
/// <summary>
|
|
/// Recognizes speech from audio bytes.
|
|
/// </summary>
|
|
/// <param name="audioBytes">Audio data in bytes (WAV format)</param>
|
|
/// <param name="sampleRate">Sample rate of the audio in Hz</param>
|
|
/// <param name="hint">Optional hint/phrase to improve recognition accuracy</param>
|
|
/// <param name="cancellationToken">Cancellation token</param>
|
|
/// <returns>Recognized text</returns>
|
|
Task<string> RecognizeSpeechAsync(
|
|
byte[] audioBytes,
|
|
int sampleRate = 16000,
|
|
string? hint = null,
|
|
CancellationToken cancellationToken = default);
|
|
|
|
/// <summary>
|
|
/// Recognizes speech from an audio file path.
|
|
/// </summary>
|
|
/// <param name="audioFilePath">Path to the audio file</param>
|
|
/// <param name="cancellationToken">Cancellation token</param>
|
|
/// <returns>Recognized text</returns>
|
|
Task<string> RecognizeSpeechFromFileAsync(
|
|
string audioFilePath,
|
|
CancellationToken cancellationToken = default);
|
|
|
|
/// <summary>
|
|
/// Recognizes speech from a stream.
|
|
/// </summary>
|
|
/// <param name="audioStream">Audio stream</param>
|
|
/// <param name="sampleRate">Sample rate of the audio in Hz</param>
|
|
/// <param name="cancellationToken">Cancellation token</param>
|
|
/// <returns>Recognized text</returns>
|
|
Task<string> RecognizeSpeechFromStreamAsync(
|
|
System.IO.Stream audioStream,
|
|
int sampleRate = 16000,
|
|
CancellationToken cancellationToken = default);
|
|
|
|
/// <summary>
|
|
/// Tests the Vosk model and configuration.
|
|
/// </summary>
|
|
/// <param name="cancellationToken">Cancellation token</param>
|
|
/// <returns>True if model is loaded and working</returns>
|
|
Task<bool> TestModelAsync(CancellationToken cancellationToken = default);
|
|
|
|
/// <summary>
|
|
/// Gets the current Vosk model information.
|
|
/// </summary>
|
|
/// <returns>Model name and path</returns>
|
|
Task<(string ModelName, string ModelPath)> GetModelInfoAsync();
|
|
}
|