C# Microsoft认知语音转换为文本-不转换整个.wav文件
当试图转换个人.wav文件时，只有一小部分语音被转换为文本，每次转换都会在完全相同的位置停止。如果有文件大小限制（我的文件是80MB），或者是因为定价层（免费），我在文档中找不到任何内容。有人知道为什么在我的例子中，三句话之后转换停止了吗？有人能给我指点吗 来自Microsoft网站的示例代码：C# Microsoft认知语音转换为文本-不转换整个.wav文件,c#,speech-to-text,microsoft-cognitive,azure-cognitive-services,C#,Speech To Text,Microsoft Cognitive,Azure Cognitive Services,当试图转换个人.wav文件时，只有一小部分语音被转换为文本，每次转换都会在完全相同的位置停止。如果有文件大小限制（我的文件是80MB），或者是因为定价层（免费），我在文档中找不到任何内容。有人知道为什么在我的例子中，三句话之后转换停止了吗？有人能给我指点吗 来自Microsoft网站的示例代码： class Program { static async Task Main() { await RecognizeSpeechA
class Program
{
static async Task Main()
{
await RecognizeSpeechAsync();
}
static async Task RecognizeSpeechAsync()
{
var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");
using (var audioInput = AudioConfig.FromWavFileInput(@"FilePath\MyWav.wav"))
using (var recognizer = new SpeechRecognizer(config, audioInput))
{
Console.WriteLine("Recognizing first result...");
var result = await recognizer.RecognizeOnceAsync();
switch (result.Reason)
{
case ResultReason.RecognizedSpeech:
Console.WriteLine($"We recognized: {result.Text}");
break;
case ResultReason.NoMatch:
Console.WriteLine($"NOMATCH: Speech could not be recognized.");
break;
case ResultReason.Canceled:
var cancellation = CancellationDetails.FromResult(result);
Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");
if (cancellation.Reason == CancellationReason.Error)
{
Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
Console.WriteLine($"CANCELED: ErrorDetails={cancellation.ErrorDetails}");
Console.WriteLine($"CANCELED: Did you update the subscription info?");
}
break;
}
}
}
}
//利用音频流进行语音识别
公共静态异步任务识别WithPullAudioStreamAsync（）
{
//使用指定的订阅密钥和服务区域创建语音配置的实例。
//替换为您自己的订阅密钥和服务区域（例如，“westus”）。
var config=SpeechConfig.FromSubscription（“YourSubscriptionKey”、“YourServiceRegion”）；
StringBuilder sb=new StringBuilder（）；//记住System.Text
var stopRecognition=new TaskCompletionSource（）；
//从wav文件创建音频流。
//替换为您自己的音频文件名。
使用（var audioInput=Helper.OpenWavFile（@“whatstheweatherlike.wav”））
{
//使用音频流输入创建语音识别器。
使用（var识别器=新的语音识别器（配置，音频输入））
{
//订阅活动。
识别器。识别+=（s，e）=>
{
//你可以不注释下面的行，但是如果你有一个像我这样的文件（80MB），你的控制台窗口会变得疯狂
//WriteLine（$“识别：Text={e.Result.Text}”）；
某人追加（如结果文本）；
};
识别器。已识别+=（s，e）=>
{
if（e.Result.Reason==ResultReason.RecognizedSpeech）
{
WriteLine（$“已识别：Text={e.Result.Text}”）；
AppendAllText（“test.txt”，e.Result.Text）；
}
else if（e.Result.Reason==ResultReason.NoMatch）
{
Console.WriteLine（$“无法识别NOMATCH:语音”）；
}
};
识别器。已取消+=（s，e）=>
{
WriteLine（$“已取消：原因={e.Reason}”）；
如果（e.Reason==CancellationReason.Error）
{
WriteLine（$“已取消：ErrorCode={e.ErrorCode}”）；
WriteLine（$“已取消：ErrorDetails={e.ErrorDetails}”）；
Console.WriteLine（$“已取消：是否更新了订阅信息？”）；
}
停止识别。TrySetResult（0）；
};
recognizer.SessionStarted+=（s，e）=>
{
Console.WriteLine（“\n会话启动事件”）；
};
recognizer.SessionStopped+=（s，e）=>
{
AppendAllText（“test.txt”，e.Result.Text）；
Console.WriteLine（“\n会话停止事件”）；
Console.WriteLine（“\n停止识别”）；
停止识别。TrySetResult（0）；
};
//启动连续识别。使用StopContinuousRecognitionAsync（）停止识别。
等待识别器。StartContinuousRecognitionAsync（）。配置等待（false）；
//等待完成。
//使用Task.WaitAny使任务保持根目录。
Task.WaitAny（新[]{stopRecognition.Task}）；
//停止识别。
等待识别器。StopContinuousRecognitionAsync（）。配置等待（false）；
}
}
}
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using System;
using System.Diagnostics;
using System.IO;
namespace MicrosoftSpeechSDKSamples
{
public class Helper
{
public static AudioConfig OpenWavFile(string filename)
{
BinaryReader reader = new BinaryReader(File.OpenRead(filename));
return OpenWavFile(reader);
}
public static AudioConfig OpenWavFile(BinaryReader reader)
{
AudioStreamFormat format = readWaveHeader(reader);
return AudioConfig.FromStreamInput(new BinaryAudioStreamReader(reader), format);
}
public static BinaryAudioStreamReader CreateWavReader(string filename)
{
BinaryReader reader = new BinaryReader(File.OpenRead(filename));
// read the wave header so that it won't get into the in the following readings
AudioStreamFormat format = readWaveHeader(reader);
return new BinaryAudioStreamReader(reader);
}
public static AudioStreamFormat readWaveHeader(BinaryReader reader)
{
// Tag "RIFF"
char[] data = new char[4];
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'R') && (data[1] == 'I') && (data[2] == 'F') && (data[3] == 'F'), "Wrong wav header");
// Chunk size
long fileSize = reader.ReadInt32();
// Subchunk, Wave Header
// Subchunk, Format
// Tag: "WAVE"
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'W') && (data[1] == 'A') && (data[2] == 'V') && (data[3] == 'E'), "Wrong wav tag in wav header");
// Tag: "fmt"
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'f') && (data[1] == 'm') && (data[2] == 't') && (data[3] == ' '), "Wrong format tag in wav header");
// chunk format size
var formatSize = reader.ReadInt32();
var formatTag = reader.ReadUInt16();
var channels = reader.ReadUInt16();
var samplesPerSecond = reader.ReadUInt32();
var avgBytesPerSec = reader.ReadUInt32();
var blockAlign = reader.ReadUInt16();
var bitsPerSample = reader.ReadUInt16();
// Until now we have read 16 bytes in format, the rest is cbSize and is ignored for now.
if (formatSize > 16)
reader.ReadBytes((int)(formatSize - 16));
// Second Chunk, data
// tag: data.
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'd') && (data[1] == 'a') && (data[2] == 't') && (data[3] == 'a'), "Wrong data tag in wav");
// data chunk size
int dataSize = reader.ReadInt32();
// now, we have the format in the format parameter and the
// reader set to the start of the body, i.e., the raw sample data
return AudioStreamFormat.GetWaveFormatPCM(samplesPerSecond, (byte)bitsPerSample, (byte)channels);
}
}
/// <summary>
/// Adapter class to the native stream api.
/// </summary>
public sealed class BinaryAudioStreamReader : PullAudioInputStreamCallback
{
private System.IO.BinaryReader _reader;
/// <summary>
/// Creates and initializes an instance of BinaryAudioStreamReader.
/// </summary>
/// <param name="reader">The underlying stream to read the audio data from. Note: The stream contains the bare sample data, not the container (like wave header data, etc).</param>
public BinaryAudioStreamReader(System.IO.BinaryReader reader)
{
_reader = reader;
}
/// <summary>
/// Creates and initializes an instance of BinaryAudioStreamReader.
/// </summary>
/// <param name="stream">The underlying stream to read the audio data from. Note: The stream contains the bare sample data, not the container (like wave header data, etc).</param>
public BinaryAudioStreamReader(System.IO.Stream stream)
: this(new System.IO.BinaryReader(stream))
{
}
/// <summary>
/// Reads binary data from the stream.
/// </summary>
/// <param name="dataBuffer">The buffer to fill</param>
/// <param name="size">The size of data in the buffer.</param>
/// <returns>The number of bytes filled, or 0 in case the stream hits its end and there is no more data available.
/// If there is no data immediate available, Read() blocks until the next data becomes available.</returns>
public override int Read(byte[] dataBuffer, uint size)
{
return _reader.Read(dataBuffer, 0, (int)size);
}
/// <summary>
/// This method performs cleanup of resources.
/// The Boolean parameter <paramref name="disposing"/> indicates whether the method is called from <see cref="IDisposable.Dispose"/> (if <paramref name="disposing"/> is true) or from the finalizer (if <paramref name="disposing"/> is false).
/// Derived classes should override this method to dispose resource if needed.
/// </summary>
/// <param name="disposing">Flag to request disposal.</param>
protected override void Dispose(bool disposing)
{
if (disposed)
{
return;
}
if (disposing)
{
_reader.Dispose();
}
disposed = true;
base.Dispose(disposing);
}
private bool disposed = false;
}
/// <summary>
/// Implements a custom class for PushAudioOutputStreamCallback.
/// This is to receive the audio data when the synthesizer has produced audio data.
/// </summary>
public sealed class PushAudioOutputStreamSampleCallback : PushAudioOutputStreamCallback
{
private byte[] audioData;
/// <summary>
/// Constructor
/// </summary>
public PushAudioOutputStreamSampleCallback()
{
audioData = new byte[0];
}
/// <summary>
/// A callback which is invoked when the synthesizer has a output audio chunk to write out
/// </summary>
/// <param name="dataBuffer">The output audio chunk sent by synthesizer</param>
/// <returns>Tell synthesizer how many bytes are received</returns>
public override uint Write(byte[] dataBuffer)
{
int oldSize = audioData.Length;
Array.Resize(ref audioData, oldSize + dataBuffer.Length);
for (int i = 0; i < dataBuffer.Length; ++i)
{
audioData[oldSize + i] = dataBuffer[i];
}
Console.WriteLine($"{dataBuffer.Length} bytes received.");
return (uint)dataBuffer.Length;
}
/// <summary>
/// A callback which is invoked when the synthesizer is about to close the stream
/// </summary>
public override void Close()
{
Console.WriteLine("Push audio output stream closed.");
}
/// <summary>
/// Get the received audio data
/// </summary>
/// <returns>The received audio data in byte array</returns>
public byte[] GetAudioData()
{
return audioData;
}
}
}
使用Microsoft.CognitiveServices.Speech；
使用Microsoft.CognitiveServices.Speech.Audio；
使用制度；
使用系统诊断；
使用System.IO；
名称空间MicrosoftSpeechSDKSamples
{
公营助理员
{
公共静态AudioConfig OpenWavFile（字符串文件名）
{
BinaryReader=新的BinaryReader（File.OpenRead（filename））；
返回OpenWavFile（读卡器）；
}
公共静态AudioConfig OpenWavFile（二进制读取器）
{
AudioStreamFormat格式=readWaveHeader（读取器）；
返回AudioConfig.FromStreamInput（新的二进制AudioStreamReader（reader），格式）；
}
公共静态二进制AudioStreamReader CreateWavReader（字符串文件名）
{
BinaryReader=新的BinaryReader（File.OpenRead（filename））；
//读取波形标题，使其不会进入以下读数中
AudioStreamFormat格式=readWaveHeader（读取器）；
返回新的BinaryAudioStreamReader（读取器）；
}
公共静态AudioStreamFormat readWaveHeader（二进制读取器）
{
//标记“RIFF”
字符[]数据=新字符[4]；
reader.Read（数据，0,4）；
Assert（（数据[0]='R'）&&（数据[1]='I'）&&（数据[2]='F'）&（数据[3]='F'），“错误的wav头”）；
//块大小
long fileSize=reader.ReadInt32（）；
//波头分块
//子块，格式
//标签：“波浪”
reader.Read（数据，0,4）；
Assert（（数据[0]='W'）&&（数据[1]='A'）&&（数据[2]='V'）&（数据[3]='E'），“wav头中的wav标记错误”）；
//标签：“fmt”
reader.Read（数据，0,4）；
Assert（（数据[0]='f'）&&（数据[1]='m'）&&（数据[2]='t'）&&（数据[3]=''，“wav头中的格式标记错误”）；
//块格式大小
var formatSize=reader.ReadInt32（）；
var formatTag=reader.ReadUIn
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using System;
using System.Diagnostics;
using System.IO;
namespace MicrosoftSpeechSDKSamples
{
public class Helper
{
public static AudioConfig OpenWavFile(string filename)
{
BinaryReader reader = new BinaryReader(File.OpenRead(filename));
return OpenWavFile(reader);
}
public static AudioConfig OpenWavFile(BinaryReader reader)
{
AudioStreamFormat format = readWaveHeader(reader);
return AudioConfig.FromStreamInput(new BinaryAudioStreamReader(reader), format);
}
public static BinaryAudioStreamReader CreateWavReader(string filename)
{
BinaryReader reader = new BinaryReader(File.OpenRead(filename));
// read the wave header so that it won't get into the in the following readings
AudioStreamFormat format = readWaveHeader(reader);
return new BinaryAudioStreamReader(reader);
}
public static AudioStreamFormat readWaveHeader(BinaryReader reader)
{
// Tag "RIFF"
char[] data = new char[4];
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'R') && (data[1] == 'I') && (data[2] == 'F') && (data[3] == 'F'), "Wrong wav header");
// Chunk size
long fileSize = reader.ReadInt32();
// Subchunk, Wave Header
// Subchunk, Format
// Tag: "WAVE"
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'W') && (data[1] == 'A') && (data[2] == 'V') && (data[3] == 'E'), "Wrong wav tag in wav header");
// Tag: "fmt"
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'f') && (data[1] == 'm') && (data[2] == 't') && (data[3] == ' '), "Wrong format tag in wav header");
// chunk format size
var formatSize = reader.ReadInt32();
var formatTag = reader.ReadUInt16();
var channels = reader.ReadUInt16();
var samplesPerSecond = reader.ReadUInt32();
var avgBytesPerSec = reader.ReadUInt32();
var blockAlign = reader.ReadUInt16();
var bitsPerSample = reader.ReadUInt16();
// Until now we have read 16 bytes in format, the rest is cbSize and is ignored for now.
if (formatSize > 16)
reader.ReadBytes((int)(formatSize - 16));
// Second Chunk, data
// tag: data.
reader.Read(data, 0, 4);
Trace.Assert((data[0] == 'd') && (data[1] == 'a') && (data[2] == 't') && (data[3] == 'a'), "Wrong data tag in wav");
// data chunk size
int dataSize = reader.ReadInt32();
// now, we have the format in the format parameter and the
// reader set to the start of the body, i.e., the raw sample data
return AudioStreamFormat.GetWaveFormatPCM(samplesPerSecond, (byte)bitsPerSample, (byte)channels);
}
}
/// <summary>
/// Adapter class to the native stream api.
/// </summary>
public sealed class BinaryAudioStreamReader : PullAudioInputStreamCallback
{
private System.IO.BinaryReader _reader;
/// <summary>
/// Creates and initializes an instance of BinaryAudioStreamReader.
/// </summary>
/// <param name="reader">The underlying stream to read the audio data from. Note: The stream contains the bare sample data, not the container (like wave header data, etc).</param>
public BinaryAudioStreamReader(System.IO.BinaryReader reader)
{
_reader = reader;
}
/// <summary>
/// Creates and initializes an instance of BinaryAudioStreamReader.
/// </summary>
/// <param name="stream">The underlying stream to read the audio data from. Note: The stream contains the bare sample data, not the container (like wave header data, etc).</param>
public BinaryAudioStreamReader(System.IO.Stream stream)
: this(new System.IO.BinaryReader(stream))
{
}
/// <summary>
/// Reads binary data from the stream.
/// </summary>
/// <param name="dataBuffer">The buffer to fill</param>
/// <param name="size">The size of data in the buffer.</param>
/// <returns>The number of bytes filled, or 0 in case the stream hits its end and there is no more data available.
/// If there is no data immediate available, Read() blocks until the next data becomes available.</returns>
public override int Read(byte[] dataBuffer, uint size)
{
return _reader.Read(dataBuffer, 0, (int)size);
}
/// <summary>
/// This method performs cleanup of resources.
/// The Boolean parameter <paramref name="disposing"/> indicates whether the method is called from <see cref="IDisposable.Dispose"/> (if <paramref name="disposing"/> is true) or from the finalizer (if <paramref name="disposing"/> is false).
/// Derived classes should override this method to dispose resource if needed.
/// </summary>
/// <param name="disposing">Flag to request disposal.</param>
protected override void Dispose(bool disposing)
{
if (disposed)
{
return;
}
if (disposing)
{
_reader.Dispose();
}
disposed = true;
base.Dispose(disposing);
}
private bool disposed = false;
}
/// <summary>
/// Implements a custom class for PushAudioOutputStreamCallback.
/// This is to receive the audio data when the synthesizer has produced audio data.
/// </summary>
public sealed class PushAudioOutputStreamSampleCallback : PushAudioOutputStreamCallback
{
private byte[] audioData;
/// <summary>
/// Constructor
/// </summary>
public PushAudioOutputStreamSampleCallback()
{
audioData = new byte[0];
}
/// <summary>
/// A callback which is invoked when the synthesizer has a output audio chunk to write out
/// </summary>
/// <param name="dataBuffer">The output audio chunk sent by synthesizer</param>
/// <returns>Tell synthesizer how many bytes are received</returns>
public override uint Write(byte[] dataBuffer)
{
int oldSize = audioData.Length;
Array.Resize(ref audioData, oldSize + dataBuffer.Length);
for (int i = 0; i < dataBuffer.Length; ++i)
{
audioData[oldSize + i] = dataBuffer[i];
}
Console.WriteLine($"{dataBuffer.Length} bytes received.");
return (uint)dataBuffer.Length;
}
/// <summary>
/// A callback which is invoked when the synthesizer is about to close the stream
/// </summary>
public override void Close()
{
Console.WriteLine("Push audio output stream closed.");
}
/// <summary>
/// Get the received audio data
/// </summary>
/// <returns>The received audio data in byte array</returns>
public byte[] GetAudioData()
{
return audioData;
}
}
}
{
"contentUrls": [
"{{path to audio blob}}"
],
"properties": {
"diarizationEnabled": false,
"wordLevelTimestampsEnabled": false,
"punctuationMode": "DictatedAndAutomatic",
"profanityFilterMode": "Masked",
"destinationContainerUrl": "{{path to your container with SAS token}}"
},
"locale": "en-US",
"displayName": "Transcription using default model for en-US",
}