add ToProviderFormat for language code conversion

This commit is contained in:
leonardotrapani
2026-02-01 00:26:17 +01:00
parent 3a1b75f58d
commit b7df5388e2
4 changed files with 102 additions and 3 deletions
+46
View File
@@ -118,3 +118,49 @@ func IsValidCode(code string) bool {
_, ok := codeIndex[code]
return ok
}
// ToProviderFormat converts a canonical language code to the format expected by a specific provider.
// Each provider may have different expectations:
// - whisper-cpp: uses standard codes like 'en', 'auto' for auto-detect
// - openai: uses standard codes like 'en', empty string for auto-detect
// - groq: same as openai (OpenAI-compatible)
// - mistral: same as openai (OpenAI-compatible)
// - deepgram: uses locale codes like 'en-US', 'es' for Spanish
// - elevenlabs: uses standard codes or full names depending on API version
func ToProviderFormat(code string, providerName string) string {
// handle auto-detect (empty code)
if code == "" {
switch providerName {
case "whisper-cpp":
return "auto"
default:
// most providers use empty string or omit the parameter
return ""
}
}
switch providerName {
case "deepgram":
// deepgram prefers locale codes for some languages
return toDeepgramFormat(code)
default:
// whisper-cpp, openai, groq, mistral, elevenlabs use standard codes
return code
}
}
// toDeepgramFormat maps standard codes to Deepgram's preferred format
func toDeepgramFormat(code string) string {
// deepgram uses locale codes for English variants, standard for most others
deepgramMappings := map[string]string{
"en": "en-US",
"es": "es", // Spanish uses base code
"pt": "pt-BR", // Portuguese defaults to Brazilian
"zh": "zh-CN", // Chinese defaults to Simplified
}
if mapped, ok := deepgramMappings[code]; ok {
return mapped
}
return code
}
+46
View File
@@ -117,3 +117,49 @@ func TestAuto(t *testing.T) {
t.Errorf("Auto.Name = %q, want 'Auto-detect'", Auto.Name)
}
}
func TestToProviderFormat(t *testing.T) {
tests := []struct {
code string
provider string
want string
}{
// whisper-cpp
{"en", "whisper-cpp", "en"},
{"es", "whisper-cpp", "es"},
{"", "whisper-cpp", "auto"},
// openai
{"en", "openai", "en"},
{"", "openai", ""},
// groq (openai-compatible)
{"en", "groq", "en"},
{"", "groq", ""},
// mistral (openai-compatible)
{"en", "mistral", "en"},
{"", "mistral", ""},
// deepgram (uses locale codes)
{"en", "deepgram", "en-US"},
{"es", "deepgram", "es"},
{"pt", "deepgram", "pt-BR"},
{"zh", "deepgram", "zh-CN"},
{"fr", "deepgram", "fr"}, // no special mapping, passthrough
{"", "deepgram", ""},
// elevenlabs
{"en", "elevenlabs", "en"},
{"", "elevenlabs", ""},
}
for _, tt := range tests {
t.Run(tt.code+"_"+tt.provider, func(t *testing.T) {
got := ToProviderFormat(tt.code, tt.provider)
if got != tt.want {
t.Errorf("ToProviderFormat(%q, %q) = %q, want %q", tt.code, tt.provider, got, tt.want)
}
})
}
}
+7
View File
@@ -9,3 +9,10 @@ Started: Sun Feb 1 12:22:47 AM CET 2026
- Implemented FromCode, List, Codes, AllLanguageCodes, IsValidCode
- Full 57 language list from OpenAI Whisper
- All tests passing, typecheck passes
### Task 2: Add language list and provider-specific mappings
- Added `ToProviderFormat(code string, providerName string) string` function
- Handles auto-detect: whisper-cpp uses "auto", others use ""
- Deepgram locale mappings: en->en-US, pt->pt-BR, zh->zh-CN
- Added comprehensive test coverage for all provider formats
- All tests passing, typecheck passes
+3 -3
View File
@@ -29,11 +29,11 @@
"passes": true
},
{
"title": "Add language list and provider-specific mappings",
"title": "Add language list and provider-specific mappings",
"steps": [
"Update internal/language/language.go with full language list",
"Master language list derived from OpenAI Whisper's 57 supported languages (source: https://platform.openai.com/docs/guides/speech-to-text#supported-languages)",
"Add all 57 languages: af/Afrikaans, ar/Arabic/العربية, hy/Armenian/Հայdelays, az/Azerbaijani/Azərbaycan, be/Belarusian/Беларуская, bs/Bosnian/Bosanski, bg/Bulgarian/Български, ca/Catalan/Català, zh/Chinese/中文, hr/Croatian/Hrvatski, cs/Czech/Čeština, da/Danish/Dansk, nl/Dutch/Nederlands, en/English, et/Estonian/Eesti, fi/Finnish/Suomi, fr/French/Français, gl/Galician/Galego, de/German/Deutsch, el/Greek/Ελληνικά, he/Hebrew/עברית, hi/Hindi/हिन्दी, hu/Hungarian/Magyar, is/Icelandic/Íslenska, id/Indonesian/Bahasa Indonesia, it/Italian/Italiano, ja/Japanese/日本語, kn/Kannada/ಕನ್ನಡ, kk/Kazakh/Қазақ, ko/Korean/한국어, lv/Latvian/Latviešu, lt/Lithuanian/Lietuvių, mk/Macedonian/Македонски, ms/Malay/Bahasa Melayu, mr/Marathi/मराठी, mi/Maori/Māori, ne/Nepali/नेपाली, no/Norwegian/Norsk, fa/Persian/فارسی, pl/Polish/Polski, pt/Portuguese/Português, ro/Romanian/Română, ru/Russian/Русский, sr/Serbian/Српски, sk/Slovak/Slovenčina, sl/Slovenian/Slovenščina, es/Spanish/Español, sw/Swahili/Kiswahili, sv/Swedish/Svenska, tl/Tagalog, ta/Tamil/தமிழ், th/Thai/ไทย, tr/Turkish/Türkçe, uk/Ukrainian/Українська, ur/Urdu/اردو, vi/Vietnamese/Tiếng Việt, cy/Welsh/Cymraeg",
"Add all 57 languages: af/Afrikaans, ar/Arabic/العربية, hy/Armenian/Հdelays, az/Azerbaijani/Azərbaycan, be/Belarusian/Беларуская, bs/Bosnian/Bosanski, bg/Bulgarian/Български, ca/Catalan/Català, zh/Chinese/中文, hr/Croatian/Hrvatski, cs/Czech/Čeština, da/Danish/Dansk, nl/Dutch/Nederlands, en/English, et/Estonian/Eesti, fi/Finnish/Suomi, fr/French/Français, gl/Galician/Galego, de/German/Deutsch, el/Greek/Ελληνικά, he/Hebrew/עברית, hi/Hindi/हिन्दी, hu/Hungarian/Magyar, is/Icelandic/Íslenska, id/Indonesian/Bahasa Indonesia, it/Italian/Italiano, ja/Japanese/日本語, kn/Kannada/ಕನ್ನಡ, kk/Kazakh/Қазақ, ko/Korean/한국어, lv/Latvian/Latviešu, lt/Lithuanian/Lietuvių, mk/Macedonian/Македонски, ms/Malay/Bahasa Melayu, mr/Marathi/मराठी, mi/Maori/Māori, ne/Nepali/नेपाली, no/Norwegian/Norsk, fa/Persian/فارسی, pl/Polish/Polski, pt/Portuguese/Português, ro/Romanian/Română, ru/Russian/Русский, sr/Serbian/Српски, sk/Slovak/Slovenčina, sl/Slovenian/Slovenščina, es/Spanish/Español, sw/Swahili/Kiswahili, sv/Swedish/Svenska, tl/Tagalog, ta/Tamil/தமிழ், th/Thai/ไทย, tr/Turkish/Türkçe, uk/Ukrainian/Українська, ur/Urdu/اردو, vi/Vietnamese/Tiếng Việt, cy/Welsh/Cymraeg",
"Implement ToProviderFormat(code string, providerName string) string - maps our code to provider-specific format",
"Provider mappings: whisper-cpp uses 'en'/'auto', some APIs use 'english', Deepgram uses 'en-US'",
"Each provider can handle Auto ('') differently via ToProviderFormat"
@@ -47,7 +47,7 @@
"ToProviderFormat('', 'openai') returns '' or appropriate auto value",
"Typecheck passes"
],
"passes": false
"passes": true
},
{
"title": "Create Model type with full metadata",