159 lines
4.5 KiB
C#
159 lines
4.5 KiB
C#
using System;
|
|
using System.IO;
|
|
using System.Linq;
|
|
using Whisper.net;
|
|
using System.Threading;
|
|
using xAiModels.Models;
|
|
using System.Threading.Tasks;
|
|
using xAiApi.Interfaces.Extractors;
|
|
using DocumentFormat.OpenXml.EMMA;
|
|
|
|
namespace xAiApi.Providers.Extractors
|
|
{
|
|
/// <summary>
|
|
/// Extracts text content from Audio files ...
|
|
/// </summary>
|
|
public class XAudioFileContentExtractor : IXAudioFileContentExtractor
|
|
{
|
|
/// <summary>
|
|
/// Supported MIME Types ...
|
|
/// </summary>
|
|
private static readonly string[] SupportedMimeTypes =
|
|
[
|
|
"audio/mpeg",
|
|
"audio/mp3",
|
|
"audio/wav",
|
|
"audio/wave",
|
|
"audio/ogg",
|
|
"audio/m4a",
|
|
"audio/mp4",
|
|
"audio/webm"
|
|
];
|
|
|
|
private readonly string language;
|
|
private readonly string whisperModelPath;
|
|
|
|
public XAudioFileContentExtractor() : this(
|
|
language: "fa",
|
|
whisperModelPath: "Models/ggml-base.bin"
|
|
)
|
|
{ }
|
|
|
|
public XAudioFileContentExtractor(
|
|
string whisperModelPath = "Models/ggml-base.bin",
|
|
string language = "fa"
|
|
)
|
|
{
|
|
//
|
|
this.language = language;
|
|
this.whisperModelPath = whisperModelPath;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Check if this extractor supports the specified MIME type ...
|
|
/// </summary>
|
|
public bool CanExtract(string mimeType)
|
|
{
|
|
//
|
|
return SupportedMimeTypes.Contains(
|
|
mimeType?.ToLowerInvariant() ?? string.Empty
|
|
);
|
|
}
|
|
|
|
/// <summary>
|
|
/// Extract text content from file stream ...
|
|
/// </summary>
|
|
public async Task<string> ExtractAsync(
|
|
Stream fileStream,
|
|
string mimeType,
|
|
CancellationToken cancellationToken = default
|
|
)
|
|
{
|
|
//
|
|
var result = await ExtractRichAsync(
|
|
fileStream,
|
|
"audio",
|
|
mimeType,
|
|
cancellationToken
|
|
);
|
|
|
|
//
|
|
return result.AudioTranscript;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Extract content from stream as Rich Result ...
|
|
/// </summary>
|
|
/// <param name="fileStream"></param>
|
|
/// <param name="fileName"></param>
|
|
/// <param name="mimeType"></param>
|
|
/// <param name="cancellationToken"></param>
|
|
/// <returns></returns>
|
|
public async Task<XFileExtractionResult> ExtractRichAsync(
|
|
Stream fileStream,
|
|
string fileName,
|
|
string mimeType,
|
|
CancellationToken cancellationToken = default
|
|
)
|
|
{
|
|
//
|
|
var result = new XFileExtractionResult
|
|
{
|
|
FileName = fileName,
|
|
MimeType = mimeType
|
|
};
|
|
|
|
//
|
|
try
|
|
{
|
|
//
|
|
using var memoryStream = new MemoryStream();
|
|
await fileStream.CopyToAsync(memoryStream, cancellationToken);
|
|
memoryStream.Position = 0;
|
|
|
|
//
|
|
using var wavStream = await ConvertToWavAsync(
|
|
memoryStream,
|
|
cancellationToken
|
|
);
|
|
|
|
//
|
|
using var factory = WhisperFactory.FromPath(whisperModelPath);
|
|
using var processor = factory.CreateBuilder()
|
|
.WithLanguage(language)
|
|
.Build();
|
|
|
|
//
|
|
var segments = new System.Text.StringBuilder();
|
|
await foreach (var segment in processor.ProcessAsync(wavStream, cancellationToken))
|
|
{
|
|
segments.Append(segment.Text);
|
|
}
|
|
|
|
//
|
|
result.AudioTranscript = segments.ToString().Trim();
|
|
result.Text = result.AudioTranscript;
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
result.ErrorMessage = $"Audio extraction failed: {ex.Message}";
|
|
}
|
|
|
|
//
|
|
return result;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Audio Format Converting ...
|
|
/// </summary>
|
|
private async Task<Stream> ConvertToWavAsync(
|
|
Stream inputStream,
|
|
CancellationToken cancellationToken
|
|
)
|
|
{
|
|
//
|
|
// TODO: Complete this ...
|
|
return await Task.FromResult(inputStream);
|
|
}
|
|
}
|
|
} |