C#で音声ファイルから文字起こし（Azure、プロキシ、時刻出力、一括、SpeechToText）

using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using System;
using System.Text;
using System.Threading.Tasks;

namespace SpeechToTextSample
{
    public class AzureSpeechToText
    {
        const string KEY = "32文字の英数字";
        const string REGION = "japaneast";
        const string LOCALE = "ja-JP";

        const string PROXY_HOST = "";
        const int PROXY_PORT = 0;

        public async Task<string> RecognizeAsync(string wavefile)
        {
            // Console.WriteLine($"RecognizeAsync: waveFile={wavefile}");

            // Azure情報の設定
            var config = SpeechConfig.FromSubscription(KEY, REGION);
            config.SpeechRecognitionLanguage = LOCALE;

            // Proxyの設定
            if (!string.IsNullOrEmpty(PROXY_HOST))
                config.SetProxy(PROXY_HOST, PROXY_PORT);

            // 文字起こし開始
            var result = await RecognizeStartAsync(config, wavefile);

            return result;
        }

        private async Task<string> RecognizeStartAsync(SpeechConfig config, string wavefile)
        {
            var sb = new StringBuilder();
            var stopRecognition = new TaskCompletionSource<int>();

            // SpeechToTextの開始
            using (var audioInput = AudioConfig.FromWavFileInput(wavefile))
            {
                using (var recognizer = new SpeechRecognizer(config, audioInput))
                {
                    // recognizer.Recognizing += (s, e) =>
                    // {
                    //     Console.WriteLine($"RECOGNIZING: Text={e.Result.Text}");
                    // };

                    recognizer.Recognized += (s, e) =>
                    {
                        if (e.Result.Reason == ResultReason.RecognizedSpeech)
                        {
                            var time = TimeSpan.FromSeconds(e.Result.OffsetInTicks / 10000000).ToString(@"hh\:mm\:ss");
                            var text = $"{time} {e.Result.Text}\n";
                            Console.Write(text);
                            sb.Append(text);
                        }
                        else if (e.Result.Reason == ResultReason.NoMatch)
                        {
                            Console.WriteLine($"NOMATCH: Speech could not be recognized.");
                        }
                    };

                    recognizer.Canceled += (s, e) =>
                    {
                        // Console.WriteLine($"CANCELED: Reason={e.Reason}");

                        if (e.Reason == CancellationReason.Error)
                        {
                            Console.WriteLine($"CANCELED: ErrorCode={e.ErrorCode}");
                            Console.WriteLine($"CANCELED: ErrorDetails={e.ErrorDetails}");
                            Console.WriteLine($"CANCELED: Did you update the subscription info?");
                            // ret = null;
                        }

                        stopRecognition.TrySetResult(0);
                    };

                    // recognizer.SessionStarted += (s, e) =>
                    // {
                    //     Console.WriteLine("\n    Session started event.");
                    // };

                    // recognizer.SessionStopped += (s, e) =>
                    // {
                    //     Console.WriteLine("\n    Session stopped event.");
                    //     Console.WriteLine("\nStop recognition.");
                    //     if (string.IsNullOrEmpty(ret))
                    //         ret = "";
                    //     stopRecognition.TrySetResult(0);
                    // };

                    // Starts continuous recognition. Uses StopContinuousRecognitionAsync() to stop recognition.
                    await recognizer.StartContinuousRecognitionAsync().ConfigureAwait(false);

                    // Waits for completion.
                    // Use Task.WaitAny to keep the task rooted.
                    Task.WaitAny(new[] { stopRecognition.Task });

                    // Stops recognition.
                    await recognizer.StopContinuousRecognitionAsync().ConfigureAwait(false);
                }
            }

            return sb.ToString();
        }
    }
}

    const string KEY = "32文字の英数字";
    const string REGION = "japaneast";
    const string LOCALE = "ja-JP";

    const string PROXY_HOST = "";
    const int PROXY_PORT = 0;

using System;
using System.Collections.Generic;
using System.IO;
using System.Threading.Tasks;

namespace SpeechToTextSample
{
    class Program
    {
        static async Task Main(string[] args)
        {
            var dir = @"C:\temp";
            var speechToText = new AzureSpeechToText();

            // ファイル一覧の取得
            var files = new List<string>();
            files.AddRange(Directory.GetFiles(dir, "*.wav"));

            // テキスト変換の開始
            foreach (var file in files)
            {
                Console.WriteLine("--------------------------");
                Console.WriteLine(file + " ... ");

                var result = await speechToText.RecognizeAsync(file);

                File.WriteAllText(file + ".txt", result);

                Console.WriteLine(file + " ... end");
                Console.WriteLine("");
                Console.WriteLine("");
                Console.WriteLine("");
            }
        }
    }
}