Add support for custom model names in audio transcription and translation APIs

Author: jamesrochabrun

README.md

@@ -194,8 +194,9 @@ public struct AudioTranscriptionParameters: Encodable {
    /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. Defaults to 0
    let temperature: Double?
 
-   public enum Model: String {
-      case whisperOne = "whisper-1"
+   public enum Model {
+      case whisperOne 
+      case custom(model: String)
    }
 
    public init(
@@ -252,8 +253,9 @@ public struct AudioTranslationParameters: Encodable {
    /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. Defaults to 0
    let temperature: Double?
 
-   public enum Model: String {
-      case whisperOne = "whisper-1"
+   public enum Model {
+      case whisperOne 
+      case custom(model: String)
    }
 
    public init(

Sources/OpenAI/Public/Parameters/Audio/AudioTranscriptionParameters.swift

@@ -28,8 +28,17 @@ public struct AudioTranscriptionParameters: Encodable {
    /// The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.
    let timestampGranularities: [String]?
 
-   public enum Model: String {
-      case whisperOne = "whisper-1"
+   public enum Model {
+      case whisperOne
+      case custom(model: String)
+      var value: String {
+         switch self {
+         case .whisperOne:
+            "whisper-1"
+         case .custom(let model):
+            model
+         }
+      }
    }
 
    enum CodingKeys: String, CodingKey {
@@ -54,7 +63,7 @@ public struct AudioTranscriptionParameters: Encodable {
    {
       self.fileName = fileName
       self.file = file
-      self.model = model.rawValue
+      self.model = model.value
       self.prompt = prompt
       self.responseFormat = responseFormat
       self.temperature = temperature

Sources/OpenAI/Public/Parameters/Audio/AudioTranslationParameters.swift

@@ -23,8 +23,18 @@ public struct AudioTranslationParameters: Encodable {
    /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. Defaults to 0
    let temperature: Double?
 
-   public enum Model: String {
-      case whisperOne = "whisper-1"
+   public enum Model {
+      case whisperOne
+      case custom(model: String)
+      
+      var value: String {
+         switch self {
+         case .whisperOne:
+            "whisper-1"
+         case .custom(let model):
+            model
+         }
+      }
    }
 
    enum CodingKeys: String, CodingKey {
@@ -45,7 +55,7 @@ public struct AudioTranslationParameters: Encodable {
    {
       self.fileName = fileName
       self.file = file
-      self.model = model.rawValue
+      self.model = model.value
       self.prompt = prompt
       self.responseFormat = responseFormat
       self.temperature = temperature