last ...
This commit is contained in:
@@ -0,0 +1,712 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="fa" dir="rtl">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>تکمیل سرویس XAudioFileContentExtractor - فن آوران ساحر علم</title>
|
||||
<style>
|
||||
:root {
|
||||
--primary: #1e3a8a;
|
||||
--secondary: #3b82f6;
|
||||
--accent: #f59e0b;
|
||||
--success: #10b981;
|
||||
--danger: #ef4444;
|
||||
--warning: #f97316;
|
||||
--bg-light: #f8fafc;
|
||||
--bg-code: #1e293b;
|
||||
--text-dark: #0f172a;
|
||||
--text-muted: #64748b;
|
||||
--border: #e2e8f0;
|
||||
}
|
||||
* { box-sizing: border-box; margin: 0; padding: 0; }
|
||||
body {
|
||||
font-family: 'Tahoma', 'Segoe UI', sans-serif;
|
||||
background: linear-gradient(135deg, #f8fafc 0%, #e0e7ff 100%);
|
||||
color: var(--text-dark);
|
||||
line-height: 1.8;
|
||||
padding: 20px;
|
||||
}
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
background: white;
|
||||
border-radius: 16px;
|
||||
box-shadow: 0 20px 60px rgba(0,0,0,0.1);
|
||||
overflow: hidden;
|
||||
}
|
||||
.header {
|
||||
background: linear-gradient(135deg, var(--primary) 0%, var(--secondary) 100%);
|
||||
color: white;
|
||||
padding: 40px;
|
||||
text-align: center;
|
||||
}
|
||||
.header h1 { font-size: 2.1em; margin-bottom: 10px; }
|
||||
.header .subtitle { font-size: 1.1em; opacity: 0.95; }
|
||||
.meta-bar {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
background: var(--bg-light);
|
||||
padding: 15px 30px;
|
||||
border-bottom: 2px solid var(--border);
|
||||
flex-wrap: wrap;
|
||||
gap: 15px;
|
||||
}
|
||||
.meta-item { display: flex; align-items: center; gap: 8px; font-size: 0.9em; color: var(--text-muted); }
|
||||
.meta-item strong { color: var(--primary); }
|
||||
.content { padding: 40px; }
|
||||
.section {
|
||||
margin-bottom: 35px;
|
||||
padding: 25px;
|
||||
background: var(--bg-light);
|
||||
border-radius: 12px;
|
||||
border-right: 5px solid var(--secondary);
|
||||
}
|
||||
.section h2 {
|
||||
color: var(--primary);
|
||||
font-size: 1.5em;
|
||||
margin-bottom: 20px;
|
||||
padding-bottom: 10px;
|
||||
border-bottom: 2px solid var(--border);
|
||||
}
|
||||
.section h3 { color: var(--secondary); font-size: 1.2em; margin: 20px 0 12px; }
|
||||
pre {
|
||||
background: var(--bg-code);
|
||||
color: #e2e8f0;
|
||||
padding: 18px;
|
||||
border-radius: 8px;
|
||||
overflow-x: auto;
|
||||
direction: ltr;
|
||||
text-align: left;
|
||||
font-family: 'Consolas', monospace;
|
||||
font-size: 0.85em;
|
||||
margin: 15px 0;
|
||||
border-right: 4px solid var(--accent);
|
||||
}
|
||||
code {
|
||||
background: #fef3c7;
|
||||
color: #92400e;
|
||||
padding: 2px 8px;
|
||||
border-radius: 4px;
|
||||
font-family: 'Consolas', monospace;
|
||||
font-size: 0.9em;
|
||||
direction: ltr;
|
||||
display: inline-block;
|
||||
}
|
||||
table {
|
||||
width: 100%;
|
||||
border-collapse: collapse;
|
||||
margin: 15px 0;
|
||||
background: white;
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
th { background: var(--primary); color: white; padding: 12px; text-align: right; }
|
||||
td { padding: 12px; border-bottom: 1px solid var(--border); }
|
||||
tr:hover { background: var(--bg-light); }
|
||||
.alert { padding: 15px 20px; border-radius: 8px; margin: 15px 0; border-right: 4px solid; }
|
||||
.alert-info { background: #dbeafe; border-color: var(--secondary); color: #1e40af; }
|
||||
.alert-success { background: #d1fae5; border-color: var(--success); color: #065f46; }
|
||||
.alert-warning { background: #fef3c7; border-color: var(--accent); color: #92400e; }
|
||||
.alert-danger { background: #fee2e2; border-color: var(--danger); color: #991b1b; }
|
||||
.footer { background: var(--primary); color: white; padding: 25px; text-align: center; }
|
||||
.toc { background: white; padding: 20px; border-radius: 10px; margin-bottom: 25px; border: 2px solid var(--border); }
|
||||
.toc h3 { color: var(--primary); margin-bottom: 15px; }
|
||||
.toc ol { padding-right: 25px; }
|
||||
.toc li { padding: 6px 0; }
|
||||
.toc a { color: var(--secondary); text-decoration: none; }
|
||||
.file-change { background: #f0f9ff; border-right: 4px solid var(--secondary); padding: 15px; margin: 10px 0; border-radius: 8px; }
|
||||
.file-change .path { font-family: 'Consolas', monospace; color: var(--primary); font-weight: bold; direction: ltr; display: inline-block; }
|
||||
.badge-modify { background: var(--warning); color: white; padding: 2px 8px; border-radius: 4px; font-size: 0.75em; margin-right: 8px; }
|
||||
.badge-new { background: var(--success); color: white; padding: 2px 8px; border-radius: 4px; font-size: 0.75em; margin-right: 8px; }
|
||||
.arch-grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)); gap: 20px; margin: 20px 0; }
|
||||
.arch-card { background: white; padding: 20px; border-radius: 10px; box-shadow: 0 4px 12px rgba(0,0,0,0.08); border-top: 4px solid var(--secondary); }
|
||||
.arch-card h4 { color: var(--primary); margin-bottom: 12px; }
|
||||
.arch-card ul { list-style: none; padding-right: 0; }
|
||||
.arch-card li { padding: 6px 0; padding-right: 20px; position: relative; }
|
||||
.arch-card li::before { content: '▸'; position: absolute; right: 0; color: var(--accent); font-weight: bold; }
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
|
||||
<div class="header">
|
||||
<h1>🎙️ تکمیل سرویس XAudioFileContentExtractor</h1>
|
||||
<div class="subtitle">پیادهسازی کامل تبدیل صوت به متن با Whisper و NAudio</div>
|
||||
</div>
|
||||
|
||||
<div class="meta-bar">
|
||||
<div class="meta-item">👨💻 <strong>توسعهدهنده:</strong> هادی خزاعی اصل</div>
|
||||
<div class="meta-item">🏢 <strong>شرکت:</strong> فن آوران ساحر علم</div>
|
||||
<div class="meta-item">📅 <strong>تاریخ:</strong> یکشنبه ۱۳ مهر ۱۴۰۵</div>
|
||||
<div class="meta-item">📦 <strong>پروژه:</strong> xAiApi</div>
|
||||
</div>
|
||||
|
||||
<div class="content">
|
||||
|
||||
<div class="toc">
|
||||
<h3>📑 فهرست مطالب</h3>
|
||||
<ol>
|
||||
<li><a href="#analysis">تحلیل وضعیت فعلی</a></li>
|
||||
<li><a href="#packages">گام ۱: نصب پکیجهای NuGet</a></li>
|
||||
<li><a href="#model">گام ۲: دانلود مدل Whisper</a></li>
|
||||
<li><a href="#config">گام ۳: پیکربندی appsettings.json</a></li>
|
||||
<li><a href="#code">گام ۴: کد کامل XAudioFileContentExtractor</a></li>
|
||||
<li><a href="#di">گام ۵: ثبت در Startup.cs</a></li>
|
||||
<li><a href="#tips">گام ۶: نکات و عیبیابی</a></li>
|
||||
</ol>
|
||||
</div>
|
||||
|
||||
<!-- Section 1: Analysis -->
|
||||
<div class="section" id="analysis">
|
||||
<h2>🔍 گام ۱: تحلیل وضعیت فعلی</h2>
|
||||
<p>با بررسی آخرین نسخه کد <code>XAudioFileContentExtractor</code>، موارد زیر شناسایی شد:</p>
|
||||
<table>
|
||||
<tr>
|
||||
<th>بخش</th>
|
||||
<th>وضعیت</th>
|
||||
<th>توضیح</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>SupportedMimeTypes</code></td>
|
||||
<td>✅ کامل</td>
|
||||
<td>پشتیبانی از MP3, WAV, OGG, M4A, WebM</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>CanExtract()</code></td>
|
||||
<td>✅ کامل</td>
|
||||
<td>تشخیص صحیح MIME Type</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ExtractAsync()</code></td>
|
||||
<td>✅ کامل</td>
|
||||
<td>Delegate به ExtractRichAsync</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ExtractRichAsync()</code></td>
|
||||
<td>⚠️ نیمهکاره</td>
|
||||
<td>ساختار اصلی وجود دارد ولی نیاز به تکمیل دارد</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ConvertToWavAsync()</code></td>
|
||||
<td>❌ خالی (TODO)</td>
|
||||
<td>فقط placeholder است و باید پیادهسازی شود</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ILogger</code></td>
|
||||
<td>❌ موجود نیست</td>
|
||||
<td>نیاز به تزریق Logger برای ثبت وقایع</td>
|
||||
</tr>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
<!-- Section 2: Packages -->
|
||||
<div class="section" id="packages">
|
||||
<h2>📦 گام ۲: نصب پکیجهای NuGet</h2>
|
||||
<pre># پکیج اصلی Whisper برای Speech-to-Text
|
||||
Install-Package Whisper.net
|
||||
|
||||
# Runtime مورد نیاز Whisper (برای CPU)
|
||||
Install-Package Whisper.net.Runtime
|
||||
|
||||
# کتابخانه NAudio برای تبدیل فرمت صوتی
|
||||
Install-Package NAudio</pre>
|
||||
|
||||
<div class="alert alert-info">
|
||||
<strong>💡 نکته:</strong> اگر از GPU NVIDIA استفاده میکنید، به جای <code>Whisper.net.Runtime</code> پکیج <code>Whisper.net.Runtime.Cuda</code> را نصب کنید تا سرعت پردازش چندین برابر شود.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Section 3: Model -->
|
||||
<div class="section" id="model">
|
||||
<h2>📥 گام ۳: دانلود مدل Whisper</h2>
|
||||
<p>مدلهای Whisper در اندازههای مختلف موجود هستند. برای زبان فارسی، مدل <code>base</code> یا <code>small</code> پیشنهاد میشود:</p>
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>مدل</th>
|
||||
<th>حجم</th>
|
||||
<th>دقت فارسی</th>
|
||||
<th>سرعت</th>
|
||||
<th>VRAM مورد نیاز</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ggml-tiny.bin</code></td>
|
||||
<td>~75 MB</td>
|
||||
<td>⭐⭐</td>
|
||||
<td>⭐⭐⭐⭐⭐</td>
|
||||
<td>~1 GB</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ggml-base.bin</code></td>
|
||||
<td>~142 MB</td>
|
||||
<td>⭐⭐⭐</td>
|
||||
<td>⭐⭐⭐⭐</td>
|
||||
<td>~1 GB</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ggml-small.bin</code></td>
|
||||
<td>~466 MB</td>
|
||||
<td>⭐⭐⭐⭐</td>
|
||||
<td>⭐⭐⭐</td>
|
||||
<td>~2 GB</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>ggml-medium.bin</code></td>
|
||||
<td>~1.5 GB</td>
|
||||
<td>⭐⭐⭐⭐⭐</td>
|
||||
<td>⭐⭐</td>
|
||||
<td>~5 GB</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
<p>دانلود از:</p>
|
||||
<pre># لینک مستقیم دانلود مدل base:
|
||||
https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin
|
||||
|
||||
# قرار دادن در مسیر:
|
||||
xAiApi/Models/ggml-base.bin</pre>
|
||||
</div>
|
||||
|
||||
<!-- Section 4: Config -->
|
||||
<div class="section" id="config">
|
||||
<h2>⚙️ گام ۴: پیکربندی appsettings.json</h2>
|
||||
<pre>{
|
||||
"AiApiConfiguration": {
|
||||
"FileExtraction": {
|
||||
"Audio": {
|
||||
"WhisperModelPath": "Models/ggml-base.bin",
|
||||
"DefaultLanguage": "fa"
|
||||
}
|
||||
}
|
||||
}
|
||||
}</pre>
|
||||
</div>
|
||||
|
||||
<!-- Section 5: Code -->
|
||||
<div class="section" id="code">
|
||||
<h2>🛠️ گام ۵: کد کامل XAudioFileContentExtractor</h2>
|
||||
|
||||
<div class="file-change">
|
||||
<span class="badge-modify">MODIFY</span>
|
||||
<span class="path">xAiApi/Providers/Extractors/XAudioFileContentExtractor.cs</span>
|
||||
</div>
|
||||
|
||||
<pre>using System;
|
||||
using System.IO;
|
||||
using System.Linq;
|
||||
using System.Text;
|
||||
using NAudio.Wave;
|
||||
using NAudio.Wave.SampleProviders;
|
||||
using Whisper.net;
|
||||
using System.Threading;
|
||||
using xAiModels.Models;
|
||||
using System.Threading.Tasks;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using xAiApi.Interfaces.Extractors;
|
||||
|
||||
namespace xAiApi.Providers.Extractors
|
||||
{
|
||||
/// <summary>
|
||||
/// Extracts text content from Audio files using Whisper ...
|
||||
/// </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"
|
||||
];
|
||||
|
||||
/// <summary>
|
||||
/// Language for Whisper STT ...
|
||||
/// </summary>
|
||||
private readonly string language;
|
||||
|
||||
/// <summary>
|
||||
/// Path to Whisper GGML model file ...
|
||||
/// </summary>
|
||||
private readonly string whisperModelPath;
|
||||
|
||||
/// <summary>
|
||||
/// Logger ...
|
||||
/// </summary>
|
||||
private readonly ILogger<XAudioFileContentExtractor> logger;
|
||||
|
||||
/// <summary>
|
||||
/// Default Constructor ...
|
||||
/// </summary>
|
||||
public XAudioFileContentExtractor()
|
||||
: this(
|
||||
logger: null,
|
||||
whisperModelPath: "Models/ggml-base.bin",
|
||||
language: "fa"
|
||||
)
|
||||
{ }
|
||||
|
||||
/// <summary>
|
||||
/// Constructor with configuration ...
|
||||
/// </summary>
|
||||
public XAudioFileContentExtractor(
|
||||
ILogger<XAudioFileContentExtractor> logger,
|
||||
string whisperModelPath = "Models/ggml-base.bin",
|
||||
string language = "fa"
|
||||
)
|
||||
{
|
||||
this.logger = logger;
|
||||
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.Text;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Extract content from stream as Rich Result ...
|
||||
/// </summary>
|
||||
public async Task<XFileExtractionResult> ExtractRichAsync(
|
||||
Stream fileStream,
|
||||
string fileName,
|
||||
string mimeType,
|
||||
CancellationToken cancellationToken = default
|
||||
)
|
||||
{
|
||||
var result = new XFileExtractionResult
|
||||
{
|
||||
FileName = fileName,
|
||||
MimeType = mimeType
|
||||
};
|
||||
|
||||
try
|
||||
{
|
||||
// ۱. کپی Stream ورودی به MemoryStream
|
||||
using var memoryStream = new MemoryStream();
|
||||
await fileStream.CopyToAsync(memoryStream, cancellationToken);
|
||||
memoryStream.Position = 0;
|
||||
|
||||
// ۲. تبدیل فرمت صوتی به WAV 16kHz Mono (مورد نیاز Whisper)
|
||||
using var wavStream = await ConvertToWavAsync(
|
||||
inputStream: memoryStream,
|
||||
mimeType: mimeType,
|
||||
cancellationToken: cancellationToken
|
||||
);
|
||||
|
||||
// ۳. بررسی وجود فایل مدل Whisper
|
||||
if (!File.Exists(whisperModelPath))
|
||||
{
|
||||
throw new FileNotFoundException(
|
||||
$"Whisper model not found at: {whisperModelPath}. " +
|
||||
"Please download from https://huggingface.co/ggerganov/whisper.cpp/tree/main"
|
||||
);
|
||||
}
|
||||
|
||||
// ۴. انجام Speech-to-Text با Whisper
|
||||
using var factory = WhisperFactory.FromPath(whisperModelPath);
|
||||
using var processor = factory.CreateBuilder()
|
||||
.WithLanguage(language)
|
||||
.Build();
|
||||
|
||||
var segments = new StringBuilder();
|
||||
|
||||
await foreach (var segment in processor.ProcessAsync(wavStream, cancellationToken))
|
||||
{
|
||||
cancellationToken.ThrowIfCancellationRequested();
|
||||
segments.Append(segment.Text);
|
||||
}
|
||||
|
||||
// ۵. تنظیم نتیجه
|
||||
result.AudioTranscript = segments.ToString().Trim();
|
||||
result.Text = result.AudioTranscript;
|
||||
|
||||
logger?.LogInformation(
|
||||
"Audio extraction completed for {FileName}: {Length} characters extracted",
|
||||
fileName,
|
||||
result.Text.Length
|
||||
);
|
||||
}
|
||||
catch (OperationCanceledException)
|
||||
{
|
||||
logger?.LogWarning("Audio extraction cancelled for file: {FileName}", fileName);
|
||||
throw;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
logger?.LogError(ex, "Audio extraction failed for file: {FileName}", fileName);
|
||||
result.ErrorMessage = $"Audio extraction failed: {ex.Message}";
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// تبدیل فرمت صوتی به WAV 16kHz 16-bit Mono ...
|
||||
/// فرمت استاندارد مورد نیاز موتور Whisper
|
||||
/// </summary>
|
||||
private async Task<Stream> ConvertToWavAsync(
|
||||
Stream inputStream,
|
||||
string mimeType,
|
||||
CancellationToken cancellationToken
|
||||
)
|
||||
{
|
||||
return await Task.Run(() =>
|
||||
{
|
||||
WaveStream reader = null;
|
||||
|
||||
try
|
||||
{
|
||||
inputStream.Position = 0;
|
||||
|
||||
// انتخاب Reader مناسب بر اساس MIME Type
|
||||
reader = CreateWaveReader(inputStream, mimeType);
|
||||
|
||||
// فرمت هدف: 16kHz, 16-bit, Mono
|
||||
var targetFormat = new WaveFormat(16000, 16, 1);
|
||||
|
||||
// تبدیل به SampleProvider برای پردازش
|
||||
ISampleProvider sampleProvider = reader.ToSampleProvider();
|
||||
|
||||
// تبدیل به Mono اگر چند کاناله باشد
|
||||
if (reader.WaveFormat.Channels > 1)
|
||||
{
|
||||
sampleProvider = sampleProvider.ToMono();
|
||||
}
|
||||
|
||||
// Resample به 16kHz اگر نرخ نمونهبرداری متفاوت باشد
|
||||
if (reader.WaveFormat.SampleRate != 16000)
|
||||
{
|
||||
sampleProvider = new WdlResamplingSampleProvider(
|
||||
sampleProvider,
|
||||
16000
|
||||
);
|
||||
}
|
||||
|
||||
// تبدیل به WaveProvider 16-bit
|
||||
var waveProvider = sampleProvider.ToWaveProvider16();
|
||||
|
||||
// نوشتن به MemoryStream موقت
|
||||
var tempStream = new MemoryStream();
|
||||
using (var writer = new WaveFileWriter(tempStream, targetFormat))
|
||||
{
|
||||
var buffer = new byte[4096];
|
||||
int bytesRead;
|
||||
|
||||
while ((bytesRead = waveProvider.Read(buffer, 0, buffer.Length)) > 0)
|
||||
{
|
||||
writer.Write(buffer, 0, bytesRead);
|
||||
}
|
||||
}
|
||||
|
||||
// ساخت MemoryStream جدید از دادههای نهایی
|
||||
// (چون WaveFileWriter پس از Dispose، stream را میبندد)
|
||||
var resultStream = new MemoryStream(tempStream.ToArray());
|
||||
tempStream.Dispose();
|
||||
|
||||
return resultStream;
|
||||
}
|
||||
finally
|
||||
{
|
||||
reader?.Dispose();
|
||||
}
|
||||
}, cancellationToken);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// ایجاد WaveStream Reader مناسب بر اساس نوع فایل صوتی ...
|
||||
/// </summary>
|
||||
private WaveStream CreateWaveReader(Stream stream, string mimeType)
|
||||
{
|
||||
return mimeType?.ToLowerInvariant() switch
|
||||
{
|
||||
"audio/mpeg" or "audio/mp3"
|
||||
=> new Mp3FileReader(stream),
|
||||
|
||||
"audio/wav" or "audio/wave"
|
||||
=> new WaveFileReader(stream),
|
||||
|
||||
// برای سایر فرمتها، ابتدا به عنوان MP3 تلاش میکنیم
|
||||
// در صورت خطا، باید از FFmpeg استفاده شود
|
||||
_ => new Mp3FileReader(stream)
|
||||
};
|
||||
}
|
||||
}
|
||||
}</pre>
|
||||
</div>
|
||||
|
||||
<!-- Section 6: DI -->
|
||||
<div class="section" id="di">
|
||||
<h2>🔌 گام ۶: ثبت در Startup.cs</h2>
|
||||
|
||||
<div class="file-change">
|
||||
<span class="badge-modify">MODIFY</span>
|
||||
<span class="path">xAiApi/Startup.cs</span>
|
||||
</div>
|
||||
|
||||
<pre>public void ConfigureServices(IServiceCollection services)
|
||||
{
|
||||
// ... (سایر ثبتها)
|
||||
|
||||
// ✅ ثبت XAudioFileContentExtractor با پیکربندی
|
||||
services.AddSingleton<IXFileContentExtractorBase>(sp =>
|
||||
{
|
||||
var logger = sp.GetRequiredService<ILogger<XAudioFileContentExtractor>>();
|
||||
var configuration = sp.GetRequiredService<IConfiguration>();
|
||||
|
||||
var modelPath = configuration.GetValue<string>(
|
||||
"AiApiConfiguration:FileExtraction:Audio:WhisperModelPath"
|
||||
) ?? "Models/ggml-base.bin";
|
||||
|
||||
var language = configuration.GetValue<string>(
|
||||
"AiApiConfiguration:FileExtraction:Audio:DefaultLanguage"
|
||||
) ?? "fa";
|
||||
|
||||
return new XAudioFileContentExtractor(
|
||||
logger: logger,
|
||||
whisperModelPath: modelPath,
|
||||
language: language
|
||||
);
|
||||
});
|
||||
|
||||
// ... (سایر ثبتها)
|
||||
}</pre>
|
||||
</div>
|
||||
|
||||
<!-- Section 7: Tips -->
|
||||
<div class="section" id="tips">
|
||||
<h2>💡 گام ۷: نکات و عیبیابی</h2>
|
||||
|
||||
<h3>۷.۱. مشکلات رایج:</h3>
|
||||
<table>
|
||||
<tr>
|
||||
<th>مشکل</th>
|
||||
<th>علت</th>
|
||||
<th>راهحل</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>FileNotFoundException</code></td>
|
||||
<td>فایل مدل Whisper یافت نشد</td>
|
||||
<td>دانلود مدل و قرار دادن در مسیر <code>Models/ggml-base.bin</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>InvalidOperationException</code> در NAudio</td>
|
||||
<td>فرمت صوتی پشتیبانی نمیشود</td>
|
||||
<td>نصب <code>MediaFoundation</code> یا استفاده از FFmpeg برای فرمتهای OGG/M4A</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>دقت پایین STT فارسی</td>
|
||||
<td>مدل base برای فارسی محدود است</td>
|
||||
<td>استفاده از مدل <code>ggml-small.bin</code> یا <code>ggml-medium.bin</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>کندی پردازش</td>
|
||||
<td>اجرا روی CPU</td>
|
||||
<td>نصب <code>Whisper.net.Runtime.Cuda</code> برای GPU</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>OutOfMemoryException</code></td>
|
||||
<td>فایل صوتی بسیار بزرگ</td>
|
||||
<td>محدود کردن حجم فایل ورودی یا تقسیم به بخشهای کوچکتر</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
<h3>۷.۲. پشتیبانی از فرمتهای OGG و M4A:</h3>
|
||||
<p>کتابخانه NAudio به صورت پیشفرض از فرمتهای <code>OGG</code> و <code>M4A</code> پشتیبانی نمیکند. برای این فرمتها دو راهحل وجود دارد:</p>
|
||||
|
||||
<div class="arch-grid">
|
||||
<div class="arch-card">
|
||||
<h4>راهحل ۱: استفاده از FFmpeg</h4>
|
||||
<ul>
|
||||
<li>نصب FFmpeg روی سرور</li>
|
||||
<li>تبدیل فرمت با Process.Start</li>
|
||||
<li>پشتیبانی از تمام فرمتها</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="arch-card">
|
||||
<h4>راهحل ۲: NAudio + MediaFoundation</h4>
|
||||
<ul>
|
||||
<li>فقط در Windows کار میکند</li>
|
||||
<li>پشتیبانی از M4A و برخی فرمتها</li>
|
||||
<li>بدون نیاز به نصب اضافی</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<h3>۷.۳. ساختار پوشه نهایی:</h3>
|
||||
<pre>xAiApi/
|
||||
├── Models/
|
||||
│ └── ggml-base.bin ← مدل Whisper
|
||||
├── tessdata/
|
||||
│ ├── fas.traineddata ← مدل Tesseract فارسی
|
||||
│ └── eng.traineddata ← مدل Tesseract انگلیسی
|
||||
├── appsettings.json ← پیکربندی
|
||||
└── Providers/
|
||||
└── Extractors/
|
||||
├── XAudioFileContentExtractor.cs ← ✅ تکمیل شده
|
||||
├── XImageFileContentExtractor.cs ← ✅ تکمیل شده
|
||||
├── XPdfFileContentExtractor.cs
|
||||
├── XDocxFileContentExtractor.cs
|
||||
├── XExcelFileContentExtractor.cs
|
||||
├── XPlainTextFileContentExtractor.cs
|
||||
├── XVisionFileContentExtractor.cs
|
||||
└── XFileContentExtractor.cs</pre>
|
||||
|
||||
<div class="alert alert-success">
|
||||
<strong>✅ خلاصه تغییرات:</strong>
|
||||
<ul style="padding-right: 25px; margin-top: 10px;">
|
||||
<li>🎙️ <strong>STT کامل:</strong> تبدیل صوت به متن با Whisper</li>
|
||||
<li>🔄 <strong>تبدیل فرمت:</strong> تبدیل خودکار MP3/WAV به 16kHz Mono با NAudio</li>
|
||||
<li>🌐 <strong>پشتیبانی فارسی:</strong> زبان پیشفرض فارسی</li>
|
||||
<li>🛡️ <strong>مدیریت خطا:</strong> بررسی وجود مدل و مدیریت استثناها</li>
|
||||
<li>📝 <strong>Logging:</strong> ثبت موفقیت/شکست با جزئیات</li>
|
||||
<li>⚡ <strong>بهینه:</strong> اجرای تبدیل فرمت در Thread جداگانه</li>
|
||||
<li>🔄 <strong>قابل لغو:</strong> پشتیبانی از CancellationToken</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="footer">
|
||||
<p><strong>👨💻 توسعهدهنده:</strong> هادی خزاعی اصل</p>
|
||||
<p><strong>🏢 شرکت:</strong> فن آوران ساحر علم</p>
|
||||
<p><strong>📅 تاریخ:</strong> یکشنبه ۱۳ مهر ۱۴۰۵</p>
|
||||
<p style="margin-top: 15px; opacity: 0.8; font-size: 0.9em;">
|
||||
🎙️ مستند فنی تکمیل سرویس XAudioFileContentExtractor - تمامی حقوق محفوظ است
|
||||
</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user