Katukagloria/fast

samples/fast-transcription/README.md

@@ -0,0 +1,14 @@
+# Examples to use Fast Transcription
+
+The Azure Speech Fast Transcription API is used to transcribe audio files with returning results synchronously and much faster than real-time audio.
+This functionality is exposed through a REST API and is easy to access from many programming languages. The samples here do **NOT** require the installation of the Cognitive Service Speech SDK, but use the REST API directly instead.
+
+For a detailed explanation see the [fast transcription documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create) and the `README.md` in the language specific subdirectories.
+
+Available samples:
+
+| Language | Directory | Description |
+| ---------- | -------- | ----------- |
+| C# | [csharp](csharp_client) | C# calling fast transcription REST API through System.Net.Http |
+| Python | [python](python_client) | Python client calling fast transcription REST API |
+| Node.js | [js/node](js_client) | Node.js client calling fast transcription REST API |

samples/fast-transcription/csharp_client/Program.cs

@@ -0,0 +1,92 @@
+using System;
+using System.Collections.Generic;
+using System.Diagnostics;
+using System.Net.Http;
+using System.Net.Http.Json;
+using System.Runtime.InteropServices;
+using System.Text.Json.Serialization;
+using Newtonsoft.Json;
+
+namespace fastTranscriptionClient
+{
+    public class FastTranscriptionOptions
+    {
+        public string[] Locales { get; set; } = { "en-US" };
+        public string ProfanityFilterMode { get; set; } = "masked";
+        public int[] Channels { get; set; } = { 0 };
+        public Dictionary<string, int> DiarizationSettings { get; set; } = new Dictionary<string, int>{
+             { "minSpeakers", 1 },
+             { "maxSpeakers", 4 }
+            };
+
+    }
+
+    public class Program
+    {
+        //Replace with your subscription key
+        public const string SubscriptionKey = "YourSubscriptionKey"; //Update with your subscription key
+
+        // Update with your service region
+        public const string Region =  "YourServiceRegion"; //Update with your service region
+
+        // locale and endpoint URL
+        private const string Locale = "en-US";
+
+        //local storage location for testing 
+        private const string DisplayName = "Fast transcription";
+
+
+        private static async Task Main(string[] args)
+        {
+            var audio_path = @"YourAudio_FilePath"; //- update to your audio file location
+            var transcription_path = @"transcription_response.json"; // path to store your transcription output
+            try
+            {
+                await TranscribeAsync(audio_path, transcription_path).ConfigureAwait(false);
+            }
+            catch (Exception ex)
+            {
+                Console.WriteLine($"An error occurred: {ex.Message}");
+            }
+        }
+
+        public static async Task TranscribeAsync(string audio_filepath, string transcriptions_filepath)
+        {
+            var fastTranscriptionEndpointPath = $"https://{Region}.api.cognitive.microsoft.com//speechtotext/transcriptions:transcribe?api-version=2024-05-15-preview";
+
+            var client = new HttpClient();
+            var request = new HttpRequestMessage(HttpMethod.Post, fastTranscriptionEndpointPath);
+
+            request.Headers.Add("Ocp-apim-subscription-key", SubscriptionKey);
+            request.Headers.Add("Accept", "application/json");
+
+
+            var content = new MultipartFormDataContent();
+
+            // Add the audio file
+            content.Add(new StreamContent(File.OpenRead(audio_filepath)), "audio", "test_call_audio.wav");
+
+            // Add definition
+            //var transcriptionDefinition = new StringContent("{\"locales\": [\"en-us\"],\"profanityfiltermode\": \"masked\", \"channels\": [0, 1]}", System.Text.Encoding.UTF8, "application/json");
+            var fastTranscriptionOptions = new FastTranscriptionOptions();
+            var transcriptionDefinition = JsonContent.Create(fastTranscriptionOptions);
+            content.Add(transcriptionDefinition, "definition");
+
+            request.Content = content;
+
+            // Make the API request
+            var response = await client.SendAsync(request).ConfigureAwait(false);
+            response.EnsureSuccessStatusCode();
+
+            var response_content = await response.Content.ReadAsStringAsync();
+            Console.WriteLine(response_content);
+
+            var response_content_json = JsonConvert.SerializeObject(JsonConvert.DeserializeObject(response_content), Formatting.Indented);
+
+            //save transcriptions to the transcriptions file location
+            await File.WriteAllTextAsync(transcriptions_filepath, response_content_json);
+            Console.WriteLine($"Response saved to {transcriptions_filepath}");
+
+        }
+    }
+}

samples/fast-transcription/csharp_client/csharp_client.csproj

@@ -0,0 +1,14 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Newtonsoft.Json" Version="13.0.3" />
+  </ItemGroup>
+
+</Project>

samples/fast-transcription/csharp_client/csharp_client.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.11.35327.3
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "csharp_client", "csharp_client.csproj", "{7965ED0C-5A0E-449A-A11E-8ADFB20F5474}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{7965ED0C-5A0E-449A-A11E-8ADFB20F5474}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{7965ED0C-5A0E-449A-A11E-8ADFB20F5474}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{7965ED0C-5A0E-449A-A11E-8ADFB20F5474}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{7965ED0C-5A0E-449A-A11E-8ADFB20F5474}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {CCC58C19-0005-4B05-A56B-0016ECEEC7C5}
+	EndGlobalSection
+EndGlobal

samples/fast-transcription/csharp_client/readme.md

@@ -0,0 +1,40 @@
+# C# Console app for .NET Core 
+
+This sample demonstrates audio transcription using the Fast Transcription API for C#. It runs under .NET 8.0 or later. 
+
+## Prerequisites
+
+1. An Azure AI Speech resource in one of the regions where the fast transcription API is available. The supported regions are: Central India, East US, Southeast Asia, and West Europe. For more information and region identifier, see [Speech service regions](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions)
+1. An audio file (less than 2 hours long and less than 200 MB in size) in one of the formats and codecs supported by the batch transcription API. For more information about supported audio formats, see [Supported audio formats](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-transcription-audio-data?tabs=portal#supported-audio-formats-and-codecs)
+1. For additional explanation, see [fast transcription documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create)
+
+
+## Build the sample
+
+* To tailor the sample to your configuration, use search and replace across the whole solution (for example, in Visual Studio, via **Edit** \> **Find and Replace** \> **Quick Replace**) to update the following strings:
+
+  * `YourSubscriptionKey`: replace with your subscription key.
+  * `YourServiceRegion`: replace with the [region](https://aka.ms/csspeech/region) your subscription is associated with.
+    For example, `westus` or `northeurope`.
+
+
+## Run the sample
+You can run the sample using Microsoft Visual Studio 2022 on Windows or using a .NET Core CLI
+
+### Using Visual Studio 2022
+
+TODO
+
+
+### Using the .NET Core CLI
+
+Navigate to the directory (samples/fast-transcription/csharp_client) that contains the sample and Run the following command
+
+```bash
+cd samples/fast-transcription/csharp_client
+dotnet run
+```
+
+## References
+
+* [fast transcription documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create)