#28 Docs

README_FASTTEXT.md

@@ -54,36 +54,40 @@ class Program
 
 ### Custom models
 
-#### Download the Pretrained Models
+The default model for this package is [quantized](https://fasttext.cc/docs/en/language-identification.html#:~:text=size%20of%20126MB%20%3B-,lid.176.ftz,-%2C%20which%20is%20the) `lid.176.ftz` (see below). 
+You can use the default model by calling the `LoadDefaultModel()` method.
 
-Depending on your needs, download one of the pretrained language identification (LID) models provided by Facebook:
+We recommend using the following models, but you can use any model depending on your needs. 
+It could even be a model for another text classinfiction tasks, e.g: 
+[supervised models](https://fasttext.cc/docs/en/supervised-tutorial.html)
 
-- For the LID model with 176 languages:
-    ```sh
-    curl --location -o /models/fasttext176.bin https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin
-    ```
+| Model       | Vendor               | Languages | Label format | Learn more | Download |
+| :---------- | :------------------- | :-------: | :----------- | :--------- | :------: |
+| **lid.176** | Meta Platforms, Inc. | 176       | `__label__en` `__label__uk` `__label__hi` | [fasttext.cc](https://fasttext.cc/docs/en/language-identification.html) | [lid.176.bin](https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin) |
+| **lid218e** | Meta Platforms, Inc. | 217       | `__label__eng_Latn` `__label__ukr_Cyrl` `__label__hin_Deva` | [@facebook/fasttext-language-identification](https://huggingface.co/facebook/fasttext-language-identification) | [model.bin](https://huggingface.co/facebook/fasttext-language-identification/resolve/main/model.bin?download=true) |
+| **GlotLID** | CIS, LMU Munich      | 2155(?)   | `__label__eng_Latn` `__label__ukr_Cyrl` `__label__hin_Deva` | [@cis-lmu/glotlid](https://huggingface.co/cis-lmu/glotlid) | [model_v3.bin](https://huggingface.co/cis-lmu/glotlid/resolve/main/model_v3.bin?download=true) |
 
-- For the LID model with 217 languages:
-    ```sh
-    curl --location -o /models/fasttext217.bin https://huggingface.co/facebook/fasttext-language-identification/resolve/main/model.bin?download=true
-    ```
+#### Use custom model in codes
 
-Learn more about these models here:
-- [176 languages](https://fasttext.cc/docs/en/language-identification.html)
-- [217 languages + script](https://huggingface.co/facebook/fasttext-language-identification)
+**You can use the model included in this NuGet package:**
+```
+using var fastText = new FastTextDetector();
+fastText.LoadDefaultModel();
+```
 
-#### Use custom model in code
+**You can specify the path to the model file:**
 ```
 using var fastText = new FastTextDetector();
 
-var modelPath = "/models/fasttext176.bin";
+var modelPath = "/path/to/model/fasttext176.bin";
 fastText.LoadModel(modelPath);
 ```
-OR
+
+**Also you can also load the model as a memory stream:**
 ```
 using var fastText = new FastTextDetector();
 
-var modelPath = "/models/fasttext176.bin";
+var modelPath = "/path/to/model/fasttext176.bin";
 using var stream = File.Open(modelPath, FileMode.Open);
 fastText.LoadModel(stream);
 ```

README_MEDIAPIPE.md

@@ -65,13 +65,23 @@ Learn more about this model here:
 - [Google AI Edge](https://ai.google.dev/edge/mediapipe/solutions/text/language_detector)
 
 #### Use custom model in code
+
+**You can use the model included in this NuGet package:**
+```
+using var mediaPipe = new MediaPipeDetector(
+    options: MediaPipeOptions.FromDefault()
+);
+```
+
+**You can specify the path to the model file:**
 ```
 var modelPath = "/models/mediapipe_language_detector.tflite";
 using var mediaPipe = new MediaPipeDetector(
     options: MediaPipeOptions.FromFile(modelPath)
 );
 ```
-OR
+
+**Also you can also load the model as a memory stream:**
 ```
 var modelPath = "/models/mediapipe_language_detector.tflite";
 using var stream = File.Open(modelPath, FileMode.Open);

src/LanguageIdentification.CLD2/CLD2Detector.cs

@@ -8,12 +8,23 @@
 namespace Panlingo.LanguageIdentification.CLD2
 {
     /// <summary>
-    /// .NET wrapper for CLD2
+    /// <para>Example:</para>
+    /// <code>
+    /// using var cld2 = new CLD2Detector();
+    /// var predictions = cld2.PredictLanguage("Привіт, як справи?");
+    /// </code>
+    /// 
+    /// <para>The using-operator is required to correctly remove unmanaged resources from memory after use.</para>
     /// </summary>
     public class CLD2Detector : IDisposable
     {
         private readonly Lazy<ImmutableHashSet<string>> _labels;
 
+        /// <summary>
+        /// <para>Creates an instance for <see cref="CLD2Detector"/>.</para>
+        /// <inheritdoc cref="CLD2Detector"/>
+        /// </summary>
+        /// <exception cref="NotSupportedException"></exception>
         public CLD2Detector()
         {
             if (!IsSupported())
@@ -44,6 +55,9 @@ public CLD2Detector()
             );
         }
 
+        /// <summary>
+        /// Checks the suitability of the current platform for use. Key criteria are the operating system and processor architecture
+        /// </summary>
         public static bool IsSupported()
         {
             return RuntimeInformation.OSArchitecture switch

src/LanguageIdentification.CLD3/CLD3Detector.cs

@@ -8,7 +8,13 @@
 namespace Panlingo.LanguageIdentification.CLD3
 {
     /// <summary>
-    /// .NET wrapper for CLD3
+    /// <para>Example:</para>
+    /// <code>
+    /// using var cld3 = new CLD3Detector(minNumBytes: 0, maxNumBytes: 512);
+    /// var prediction = cld3.PredictLanguage("Привіт, як справи?");
+    /// </code>
+    /// 
+    /// <para>The using-operator is required to correctly remove unmanaged resources from memory after use.</para>
     /// </summary>
     public class CLD3Detector : IDisposable
     {
@@ -17,6 +23,11 @@ public class CLD3Detector : IDisposable
         private IntPtr _detector;
         private bool _disposed = false;
 
+        /// <summary>
+        /// <para>Creates an instance for <see cref="CLD3Detector"/>.</para>
+        /// <inheritdoc cref="CLD3Detector"/>
+        /// </summary>
+        /// <exception cref="NotSupportedException"></exception>
         public CLD3Detector(int minNumBytes, int maxNumBytes)
         {
             if (!IsSupported())
@@ -51,6 +62,9 @@ public CLD3Detector(int minNumBytes, int maxNumBytes)
             );
         }
 
+        /// <summary>
+        /// Checks the suitability of the current platform for use. Key criteria are the operating system and processor architecture
+        /// </summary>
         public static bool IsSupported()
         {
             return RuntimeInformation.OSArchitecture switch

src/LanguageIdentification.FastText/FastTextDetector.cs

@@ -9,14 +9,30 @@
 namespace Panlingo.LanguageIdentification.FastText
 {
     /// <summary>
-    /// .NET wrapper for FastText
+    /// <para>Example:</para>
+    /// <code>
+    /// using var fastText = new FastTextDetector();
+    /// fastText.LoadDefaultModel();
+    /// 
+    /// var predictions = fastText.Predict(
+    ///     text: "Привіт, як справи?", 
+    ///     count: 10
+    /// );
+    /// </code>
+    /// 
+    /// <para>The using-operator is required to correctly remove unmanaged resources from memory after use.</para>
     /// </summary>
     public class FastTextDetector : IDisposable
     {
         private IntPtr _detector;
         private readonly SemaphoreSlim _semaphore;
         private bool _disposed = false;
 
+        /// <summary>
+        /// <para>Creates an instance for <see cref="FastTextDetector"/>.</para>
+        /// <inheritdoc cref="FastTextDetector"/>
+        /// </summary>
+        /// <exception cref="NotSupportedException"></exception>
         public FastTextDetector()
         {
             if (!IsSupported())
@@ -30,6 +46,9 @@ public FastTextDetector()
             _semaphore = new SemaphoreSlim(1, 1);
         }
 
+        /// <summary>
+        /// Checks the suitability of the current platform for use. Key criteria are the operating system and processor architecture
+        /// </summary>
         public static bool IsSupported()
         {
             return RuntimeInformation.OSArchitecture switch
@@ -45,7 +64,7 @@ Architecture.Arm64 when RuntimeInformation.IsOSPlatform(OSPlatform.OSX) => true,
         public string ModelPath { get; private set; } = string.Empty;
 
         /// <summary>
-        /// Loads model file located on path
+        /// Loads model file located on path. Supports *.bin or *.ftz file formats.
         /// </summary>
         /// <param name="path">Path to *.bin or *.ftz model file</param>
         public void LoadModel(string path)
@@ -68,7 +87,7 @@ public void LoadModel(string path)
         }
 
         /// <summary>
-        /// Loads model file from binary stream
+        /// Loads model file from binary stream. Supports *.bin or *.ftz file formats.
         /// </summary>
         /// <param name="stream">Stream of *.bin or *.ftz model file</param>
         public void LoadModel(Stream stream)

src/LanguageIdentification.Lingua/LinguaDetector.cs

@@ -9,7 +9,7 @@
 namespace Panlingo.LanguageIdentification.Lingua
 {
     /// <summary>
-    /// .NET wrapper for Lingua
+    /// <inheritdoc cref="LinguaDetectorBuilder"/>
     /// </summary>
     public class LinguaDetector : IDisposable
     {
@@ -42,6 +42,9 @@
             );
         }
 
+        /// <summary>
+        /// Checks the suitability of the current platform for use. Key criteria are the operating system and processor architecture
+        /// </summary>
         public static bool IsSupported()
         {
             return RuntimeInformation.OSArchitecture switch
@@ -151,6 +154,12 @@
             }
         }
 
+        /// <summary>
+        /// Converts <see cref="LinguaLanguage"/> to ISO 639-1 or ISO 639-3 string.
+        /// </summary>
+        /// <param name="language"></param>
+        /// <returns>Language code according to ISO 639-1 or ISO 639-3</returns>
+        /// <exception cref="WhatlangDetectorException"></exception>
         public string GetLanguageCode(LinguaLanguage language, LinguaLanguageCode code)
         {
             CheckDisposed();

src/LanguageIdentification.Lingua/LinguaDetectorBuilder.cs

@@ -5,14 +5,30 @@
 namespace Panlingo.LanguageIdentification.Lingua
 {
     /// <summary>
-    /// .NET wrapper for Lingua
+    /// <para>Example:</para>
+    /// <code>
+    /// using var linguaBuilder = new LinguaDetectorBuilder(Enum.GetValues&lt;LinguaLanguage&gt;())
+    ///     .WithPreloadedLanguageModels()     // optional
+    ///     .WithMinimumRelativeDistance(0.95) // optional
+    ///     .WithLowAccuracyMode();            // optional
+    ///     
+    /// using var lingua = linguaBuilder.Build();
+    /// var predictions = lingua.PredictLanguages("Привіт, як справи?");
+    /// </code>
+    /// 
+    /// <para>The using-operator is required to correctly remove unmanaged resources from memory after use.</para>
     /// </summary>
     public class LinguaDetectorBuilder : IDisposable
     {
         private readonly LinguaLanguage[] _languages;
         private IntPtr _builder;
         private bool _disposed = false;
 
+        /// <summary>
+        /// <para>Creates an instance for <see cref="LinguaDetectorBuilder"/>.</para>
+        /// <inheritdoc cref="LinguaDetectorBuilder"/>
+        /// </summary>
+        /// <exception cref="NotSupportedException"></exception>
         public LinguaDetectorBuilder(LinguaLanguage[] languages)
         {
             if (!LinguaDetector.IsSupported())

src/LanguageIdentification.MediaPipe/MediaPipeDetector.cs

@@ -10,7 +10,16 @@
 namespace Panlingo.LanguageIdentification.MediaPipe
 {
     /// <summary>
-    /// .NET wrapper for MediaPipe
+    /// <para>Example:</para>
+    /// <code>
+    /// using var mediaPipe = new MediaPipeDetector(
+    ///     options: MediaPipeOptions.FromDefault()
+    /// );
+    /// 
+    /// var predictions = mediaPipe.PredictLanguages("Привіт, як справи?");
+    /// </code>
+    /// 
+    /// <para>The using-operator is required to correctly remove unmanaged resources from memory after use.</para>
     /// </summary>
     public class MediaPipeDetector : IDisposable
     {
@@ -22,6 +31,11 @@ public class MediaPipeDetector : IDisposable
 
         private const string LABEL_FILE_NAME = "labels.txt";
 
+        /// <summary>
+        /// <para>Creates an instance for <see cref="MediaPipeDetector"/>.</para>
+        /// <inheritdoc cref="MediaPipeDetector"/>
+        /// </summary>
+        /// <exception cref="NotSupportedException"></exception>
         public MediaPipeDetector(MediaPipeOptions options)
         {
             if (!IsSupported())
@@ -66,6 +80,7 @@ public MediaPipeDetector(MediaPipeOptions options)
                 throw new InvalidOperationException("Model data not specified");
             }
 
+            // The *.tflite is actually a zip archive. We need to read ‘labels.txt’ inside to get a list of labels.
             _labels = new Lazy<ImmutableHashSet<string>>(
                 () =>
                 {
@@ -128,6 +143,9 @@ public MediaPipeDetector(MediaPipeOptions options)
             }
         }
 
+        /// <summary>
+        /// Checks the suitability of the current platform for use. Key criteria are the operating system and processor architecture
+        /// </summary>
         public static bool IsSupported()
         {
             return RuntimeInformation.OSArchitecture switch

src/LanguageIdentification.Whatlang.Native/Native/whatlang-ffi/src/lib.rs

@@ -92,30 +92,30 @@ pub enum WhatlangLanguage {
 #[repr(u8)]
 #[derive(Debug, Copy, Clone)]
 pub enum WhatlangScript {
-    Arabic = 0,
-    Armenian = 1,
-    Bengali = 2,
-    Cyrillic = 3,
-    Devanagari = 4,
-    Ethiopic = 5,
-    Georgian = 6,
-    Greek = 7,
-    Gujarati = 8,
-    Gurmukhi = 9,
-    Hangul = 10,
-    Hebrew = 11,
-    Hiragana = 12,
-    Kannada = 13,
-    Katakana = 14,
-    Khmer = 15,
-    Latin = 16,
-    Malayalam = 17,
-    Mandarin = 18,
-    Myanmar = 19,
-    Oriya = 20,
-    Sinhala = 21,
-    Tamil = 22,
-    Telugu = 23,
+    Arab = 0,
+    Armn = 1,
+    Beng = 2,
+    Cyrl = 3,
+    Deva = 4,
+    Ethi = 5,
+    Geor = 6,
+    Grek = 7,
+    Gujr = 8,
+    Guru = 9,
+    Hang = 10,
+    Hebr = 11,
+    Hira = 12,
+    Knda = 13,
+    Kana = 14,
+    Khmr = 15,
+    Latn = 16,
+    Mlym = 17,
+    Mand = 18,
+    Mymr = 19,
+    Orya = 20,
+    Sinh = 21,
+    Taml = 22,
+    Telu = 23,
     Thai = 24,
 }