Change over "speech" to "audio".

ServiceStack · Oct 14, 2024 · 960888d · 960888d
1 parent ed23a0c
commit 960888d
Show file tree

Hide file tree

Showing 7 changed files with 11 additions and 15 deletions.
diff --git a/AiServer.ServiceInterface/Jobs/CreateGenerationCommand.cs b/AiServer.ServiceInterface/Jobs/CreateGenerationCommand.cs
@@ -99,9 +99,6 @@ private async Task HandleFileUploadsTask(BackgroundJob job, GenerationArgs argIn
                 case "mask":
                     argInstance.MaskInput = ms;
                     break;
-                case "speech":
-                    argInstance.SpeechInput = ms;
-                    break;
                 case "audio":
                     argInstance.AudioInput = ms;
                     break;
@@ -113,7 +110,6 @@ private async Task HandleFileUploadsTask(BackgroundJob job, GenerationArgs argIn
     {
         "image",
         "mask",
-        "speech",
         "audio"
     };
 

diff --git a/AiServer.ServiceInterface/MediaProviderServices.cs b/AiServer.ServiceInterface/MediaProviderServices.cs
@@ -196,7 +196,7 @@ private string GetFileExtension(string contentType)
         };
     }
 
-    private static string[] supportedUploadNames = ["speech", "audio", "image", "mask"];
+    private static string[] supportedUploadNames = ["audio", "image", "mask"];
 
     public object Any(QueryMediaModels request)
     {

diff --git a/AiServer.ServiceInterface/SpeechServices.cs b/AiServer.ServiceInterface/SpeechServices.cs
@@ -38,7 +38,7 @@ public async Task<object> Any(QueueSpeechToText request)
         if(Request?.Files == null || Request.Files.Length == 0)
         {
             log.LogError("No files attached to request");
-            throw new ArgumentNullException(nameof(request.Speech));
+            throw new ArgumentNullException(nameof(request.Audio));
         }
 
         var diffRequest = new CreateGeneration
@@ -50,7 +50,7 @@ public async Task<object> Any(QueueSpeechToText request)
             {
                 Model = "speech-to-text",
                 TaskType = AiTaskType.SpeechToText,
-                SpeechInput = request.Speech
+                SpeechInput = request.Audio
             }
         };
 
@@ -81,7 +81,7 @@ public async Task<object> Any(SpeechToText request)
         if(Request?.Files == null || Request.Files.Length == 0)
         {
             log.LogError("No files attached to request");
-            throw new ArgumentNullException(nameof(request.Speech));
+            throw new ArgumentNullException(nameof(request.Audio));
         }
 
         var diffRequest = new CreateGeneration
@@ -90,7 +90,7 @@ public async Task<object> Any(SpeechToText request)
             {
                 Model = "speech-to-text",
                 TaskType = AiTaskType.SpeechToText,
-                SpeechInput = request.Speech
+                SpeechInput = request.Audio
             }
         };
 

diff --git a/AiServer.ServiceModel/Generations.cs b/AiServer.ServiceModel/Generations.cs
@@ -19,7 +19,7 @@ public class SpeechToText : IGeneration, IReturn<GenerationResponse>
     [Description("The audio stream containing the speech to be transcribed")]
     [Required]
     [Input(Type = "file")]
-    public Stream Speech { get; set; }
+    public Stream Audio { get; set; }
 
     [ApiMember(Description = "Optional client-provided identifier for the request")]
     [Description("Optional client-provided identifier for the request")]

diff --git a/AiServer.ServiceModel/QueueGenerations.cs b/AiServer.ServiceModel/QueueGenerations.cs
@@ -14,7 +14,7 @@ public class QueueSpeechToText : IQueueGeneration, IReturn<QueueGenerationRespon
     [Description("The audio stream containing the speech to be transcribed")]
     [Required]
     [Input(Type = "file")]
-    public Stream Speech { get; set; }
+    public Stream Audio { get; set; }
 
     [ApiMember(Description = "Optional client-provided identifier for the request")]
     [Description("Optional client-provided identifier for the request")]

diff --git a/AiServer.Tests/QueueSpeechToTextTests.cs b/AiServer.Tests/QueueSpeechToTextTests.cs
@@ -29,7 +29,7 @@ public async Task Can_queue_transcribe_speech()
             response = client.PostFilesWithRequest<QueueGenerationResponse>(new QueueSpeechToText
             {
 
-            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "speech"} });
+            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "audio"} });
         }
         catch (Exception e)
         {
@@ -61,7 +61,7 @@ public async Task Can_transcribe_speech_with_reply_to()
             response = client.PostFilesWithRequest<QueueGenerationResponse>(new QueueSpeechToText
             {
                 ReplyTo = "https://localhost:5005/dummyreplyto"
-            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "speech"} });
+            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "audio"} });
         }
         catch (Exception e)
         {
@@ -131,7 +131,7 @@ public async Task Can_transcribe_speech_without_sync_or_reply_to()
             response = client.PostFilesWithRequest<QueueGenerationResponse>(new QueueSpeechToText
             {
 
-            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "speech"} });
+            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "audio"} });
         }
         catch (Exception e)
         {

diff --git a/AiServer.Tests/SpeechToTextTests.cs b/AiServer.Tests/SpeechToTextTests.cs
@@ -23,7 +23,7 @@ public async Task Can_transcribe_speech()
             response = client.PostFilesWithRequest<GenerationResponse>(new SpeechToText
             {
 
-            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "speech"} });
+            }, new []{ new UploadFile("speech.wav", fileStream) { FieldName = "audio"} });
         }
         catch (Exception e)
         {
-Original file line number
+Diff line change
@@ Expand Up / @@ -196,7 +196,7 @@ private string GetFileExtension(string contentType) @@
             };
         }
-        private static string[] supportedUploadNames = ["speech", "audio", "image", "mask"];
+        private static string[] supportedUploadNames = ["audio", "image", "mask"];
         public object Any(QueryMediaModels request)
         {
@@ Expand Down @@