fixed compilation error

argmaxinc · Apr 15, 2024 · 083fe58 · 083fe58
1 parent a39cf65
commit 083fe58
Show file tree

Hide file tree

Showing 2 changed files with 123 additions and 125 deletions.
diff --git a/Sources/WhisperKit/Core/Models.swift b/Sources/WhisperKit/Core/Models.swift
@@ -906,128 +906,6 @@ public class TextDecoderCachePrefillOutput: MLFeatureProvider {
  }
 }
 
-// MARK: Languages
-
-@available(macOS 13, iOS 16, watchOS 10, visionOS 1, *)
-public extension WhisperKit {
- static var languages: [String: String] {
- [
- "english": "en",
- "chinese": "zh",
- "german": "de",
- "spanish": "es",
- "russian": "ru",
- "korean": "ko",
- "french": "fr",
- "japanese": "ja",
- "portuguese": "pt",
- "turkish": "tr",
- "polish": "pl",
- "catalan": "ca",
- "dutch": "nl",
- "arabic": "ar",
- "swedish": "sv",
- "italian": "it",
- "indonesian": "id",
- "hindi": "hi",
- "finnish": "fi",
- "vietnamese": "vi",
- "hebrew": "he",
- "ukrainian": "uk",
- "greek": "el",
- "malay": "ms",
- "czech": "cs",
- "romanian": "ro",
- "danish": "da",
- "hungarian": "hu",
- "tamil": "ta",
- "norwegian": "no",
- "thai": "th",
- "urdu": "ur",
- "croatian": "hr",
- "bulgarian": "bg",
- "lithuanian": "lt",
- "latin": "la",
- "maori": "mi",
- "malayalam": "ml",
- "welsh": "cy",
- "slovak": "sk",
- "telugu": "te",
- "persian": "fa",
- "latvian": "lv",
- "bengali": "bn",
- "serbian": "sr",
- "azerbaijani": "az",
- "slovenian": "sl",
- "kannada": "kn",
- "estonian": "et",
- "macedonian": "mk",
- "breton": "br",
- "basque": "eu",
- "icelandic": "is",
- "armenian": "hy",
- "nepali": "ne",
- "mongolian": "mn",
- "bosnian": "bs",
- "kazakh": "kk",
- "albanian": "sq",
- "swahili": "sw",
- "galician": "gl",
- "marathi": "mr",
- "punjabi": "pa",
- "sinhala": "si",
- "khmer": "km",
- "shona": "sn",
- "yoruba": "yo",
- "somali": "so",
- "afrikaans": "af",
- "occitan": "oc",
- "georgian": "ka",
- "belarusian": "be",
- "tajik": "tg",
- "sindhi": "sd",
- "gujarati": "gu",
- "amharic": "am",
- "yiddish": "yi",
- "lao": "lo",
- "uzbek": "uz",
- "faroese": "fo",
- "haitian creole": "ht",
- "pashto": "ps",
- "turkmen": "tk",
- "nynorsk": "nn",
- "maltese": "mt",
- "sanskrit": "sa",
- "luxembourgish": "lb",
- "myanmar": "my",
- "tibetan": "bo",
- "tagalog": "tl",
- "malagasy": "mg",
- "assamese": "as",
- "tatar": "tt",
- "hawaiian": "haw",
- "lingala": "ln",
- "hausa": "ha",
- "bashkir": "ba",
- "javanese": "jw",
- "sundanese": "su",
- "cantonese": "yue",
- "burmese": "my",
- "valencian": "ca",
- "flemish": "nl",
- "haitian": "ht",
- "letzeburgesch": "lb",
- "pushto": "ps",
- "panjabi": "pa",
- "moldavian": "ro",
- "moldovan": "ro",
- "sinhalese": "si",
- "castilian": "es",
- "mandarin": "zh",
- ]
- }
-}
-
 // MARK: SpecialTokens
 
 public struct SpecialTokens {
@@ -1099,7 +977,7 @@ struct WhisperTokenizerWrapper: WhisperTokenizer {
  self.tokenizer = tokenizer
  self.specialTokens = specialTokens
  self.allLanguageTokens = Set(
- WhisperKit.languages
+ Constants.languages
  .compactMap { tokenizer.convertTokenToId("<|\($0.value)|>") }
  .filter { $0 > specialTokens.specialTokenBegin }
  )
@@ -1248,3 +1126,123 @@ extension WhisperTokenizerWrapper {
  static var defaultNoTimestampsToken: Int { 50363 }
  static var defaultTimeTokenBegin: Int { 50364 }
 }
+
+// MARK: Constants
+
+public enum Constants {
+ public static let languages: [String: String] =
+ [
+ "english": "en",
+ "chinese": "zh",
+ "german": "de",
+ "spanish": "es",
+ "russian": "ru",
+ "korean": "ko",
+ "french": "fr",
+ "japanese": "ja",
+ "portuguese": "pt",
+ "turkish": "tr",
+ "polish": "pl",
+ "catalan": "ca",
+ "dutch": "nl",
+ "arabic": "ar",
+ "swedish": "sv",
+ "italian": "it",
+ "indonesian": "id",
+ "hindi": "hi",
+ "finnish": "fi",
+ "vietnamese": "vi",
+ "hebrew": "he",
+ "ukrainian": "uk",
+ "greek": "el",
+ "malay": "ms",
+ "czech": "cs",
+ "romanian": "ro",
+ "danish": "da",
+ "hungarian": "hu",
+ "tamil": "ta",
+ "norwegian": "no",
+ "thai": "th",
+ "urdu": "ur",
+ "croatian": "hr",
+ "bulgarian": "bg",
+ "lithuanian": "lt",
+ "latin": "la",
+ "maori": "mi",
+ "malayalam": "ml",
+ "welsh": "cy",
+ "slovak": "sk",
+ "telugu": "te",
+ "persian": "fa",
+ "latvian": "lv",
+ "bengali": "bn",
+ "serbian": "sr",
+ "azerbaijani": "az",
+ "slovenian": "sl",
+ "kannada": "kn",
+ "estonian": "et",
+ "macedonian": "mk",
+ "breton": "br",
+ "basque": "eu",
+ "icelandic": "is",
+ "armenian": "hy",
+ "nepali": "ne",
+ "mongolian": "mn",
+ "bosnian": "bs",
+ "kazakh": "kk",
+ "albanian": "sq",
+ "swahili": "sw",
+ "galician": "gl",
+ "marathi": "mr",
+ "punjabi": "pa",
+ "sinhala": "si",
+ "khmer": "km",
+ "shona": "sn",
+ "yoruba": "yo",
+ "somali": "so",
+ "afrikaans": "af",
+ "occitan": "oc",
+ "georgian": "ka",
+ "belarusian": "be",
+ "tajik": "tg",
+ "sindhi": "sd",
+ "gujarati": "gu",
+ "amharic": "am",
+ "yiddish": "yi",
+ "lao": "lo",
+ "uzbek": "uz",
+ "faroese": "fo",
+ "haitian creole": "ht",
+ "pashto": "ps",
+ "turkmen": "tk",
+ "nynorsk": "nn",
+ "maltese": "mt",
+ "sanskrit": "sa",
+ "luxembourgish": "lb",
+ "myanmar": "my",
+ "tibetan": "bo",
+ "tagalog": "tl",
+ "malagasy": "mg",
+ "assamese": "as",
+ "tatar": "tt",
+ "hawaiian": "haw",
+ "lingala": "ln",
+ "hausa": "ha",
+ "bashkir": "ba",
+ "javanese": "jw",
+ "sundanese": "su",
+ "cantonese": "yue",
+ "burmese": "my",
+ "valencian": "ca",
+ "flemish": "nl",
+ "haitian": "ht",
+ "letzeburgesch": "lb",
+ "pushto": "ps",
+ "panjabi": "pa",
+ "moldavian": "ro",
+ "moldovan": "ro",
+ "sinhalese": "si",
+ "castilian": "es",
+ "mandarin": "zh",
+ ]
+}
diff --git a/Sources/WhisperKitCLI/Transcribe.swift b/Sources/WhisperKitCLI/Transcribe.swift
@@ -17,8 +17,8 @@ struct Transcribe: AsyncParsableCommand {
 
  mutating func validate() throws {
  if let language = cliArguments.language {
- if !WhisperKit.languages.values.contains(language) {
- throw ValidationError("Invalid language code \"\(language)\". Supported languages: \(WhisperKit.languages.values)")
+ if !Constants.languages.values.contains(language) {
+ throw ValidationError("Invalid language code \"\(language)\". Supported languages: \(Constants.languages.values)")
  }
  }
  }