what languages this model support and is there any video tutorial?

[margo2130]

i want to know what languages this model support?
i want to convert audio to text in Persian (Farsi) language. what model do u use?
i am using now subtitle edit program.

and is there any full tutorial video for this project?

[KitaitiMakoto]

You can see the language list here:

whisper.cpp/src/whisper.cpp

Lines 246 to 347 in 021eef1

	static const std::map<std::string, std::pair<int, std::string>> g_lang = {
	{ "en", { 0, "english", } },
	{ "zh", { 1, "chinese", } },
	{ "de", { 2, "german", } },
	{ "es", { 3, "spanish", } },
	{ "ru", { 4, "russian", } },
	{ "ko", { 5, "korean", } },
	{ "fr", { 6, "french", } },
	{ "ja", { 7, "japanese", } },
	{ "pt", { 8, "portuguese", } },
	{ "tr", { 9, "turkish", } },
	{ "pl", { 10, "polish", } },
	{ "ca", { 11, "catalan", } },
	{ "nl", { 12, "dutch", } },
	{ "ar", { 13, "arabic", } },
	{ "sv", { 14, "swedish", } },
	{ "it", { 15, "italian", } },
	{ "id", { 16, "indonesian", } },
	{ "hi", { 17, "hindi", } },
	{ "fi", { 18, "finnish", } },
	{ "vi", { 19, "vietnamese", } },
	{ "he", { 20, "hebrew", } },
	{ "uk", { 21, "ukrainian", } },
	{ "el", { 22, "greek", } },
	{ "ms", { 23, "malay", } },
	{ "cs", { 24, "czech", } },
	{ "ro", { 25, "romanian", } },
	{ "da", { 26, "danish", } },
	{ "hu", { 27, "hungarian", } },
	{ "ta", { 28, "tamil", } },
	{ "no", { 29, "norwegian", } },
	{ "th", { 30, "thai", } },
	{ "ur", { 31, "urdu", } },
	{ "hr", { 32, "croatian", } },
	{ "bg", { 33, "bulgarian", } },
	{ "lt", { 34, "lithuanian", } },
	{ "la", { 35, "latin", } },
	{ "mi", { 36, "maori", } },
	{ "ml", { 37, "malayalam", } },
	{ "cy", { 38, "welsh", } },
	{ "sk", { 39, "slovak", } },
	{ "te", { 40, "telugu", } },
	{ "fa", { 41, "persian", } },
	{ "lv", { 42, "latvian", } },
	{ "bn", { 43, "bengali", } },
	{ "sr", { 44, "serbian", } },
	{ "az", { 45, "azerbaijani", } },
	{ "sl", { 46, "slovenian", } },
	{ "kn", { 47, "kannada", } },
	{ "et", { 48, "estonian", } },
	{ "mk", { 49, "macedonian", } },
	{ "br", { 50, "breton", } },
	{ "eu", { 51, "basque", } },
	{ "is", { 52, "icelandic", } },
	{ "hy", { 53, "armenian", } },
	{ "ne", { 54, "nepali", } },
	{ "mn", { 55, "mongolian", } },
	{ "bs", { 56, "bosnian", } },
	{ "kk", { 57, "kazakh", } },
	{ "sq", { 58, "albanian", } },
	{ "sw", { 59, "swahili", } },
	{ "gl", { 60, "galician", } },
	{ "mr", { 61, "marathi", } },
	{ "pa", { 62, "punjabi", } },
	{ "si", { 63, "sinhala", } },
	{ "km", { 64, "khmer", } },
	{ "sn", { 65, "shona", } },
	{ "yo", { 66, "yoruba", } },
	{ "so", { 67, "somali", } },
	{ "af", { 68, "afrikaans", } },
	{ "oc", { 69, "occitan", } },
	{ "ka", { 70, "georgian", } },
	{ "be", { 71, "belarusian", } },
	{ "tg", { 72, "tajik", } },
	{ "sd", { 73, "sindhi", } },
	{ "gu", { 74, "gujarati", } },
	{ "am", { 75, "amharic", } },
	{ "yi", { 76, "yiddish", } },
	{ "lo", { 77, "lao", } },
	{ "uz", { 78, "uzbek", } },
	{ "fo", { 79, "faroese", } },
	{ "ht", { 80, "haitian creole", } },
	{ "ps", { 81, "pashto", } },
	{ "tk", { 82, "turkmen", } },
	{ "nn", { 83, "nynorsk", } },
	{ "mt", { 84, "maltese", } },
	{ "sa", { 85, "sanskrit", } },
	{ "lb", { 86, "luxembourgish", } },
	{ "my", { 87, "myanmar", } },
	{ "bo", { 88, "tibetan", } },
	{ "tl", { 89, "tagalog", } },
	{ "mg", { 90, "malagasy", } },
	{ "as", { 91, "assamese", } },
	{ "tt", { 92, "tatar", } },
	{ "haw", { 93, "hawaiian", } },
	{ "ln", { 94, "lingala", } },
	{ "ha", { 95, "hausa", } },
	{ "ba", { 96, "bashkir", } },
	{ "jw", { 97, "javanese", } },
	{ "su", { 98, "sundanese", } },
	{ "yue", { 99, "cantonese", } },
	};

Persian seems to be supported.

I don't know tutorial videos.

[MathiasSchindler]

@margo2130 As you can read from the announcement of the large-v3 model, Persian (Farsi) is among the supported languages.

openai/whisper#1762 However, the quality of the recognition of text might not be as good as with other languages. While smaller models such as tiny, base, small and medium would in theory also work with Persian, the problems with errors in recognition might be much higher. Only the ".en" versions are English-only (such as tiny.en oder small.en).

The "Quick start" section of the page at https://github.com/ggerganov/whisper.cpp will give you the kind of tutorial in text form that you might be looking for.

[margo2130]

@margo2130 As you can read from the announcement of the large-v3 model, Persian (Farsi) is among the supported languages.

openai/whisper#1762 However, the quality of the recognition of text might not be as good as with other languages. While smaller models such as tiny, base, small and medium would in theory also work with Persian, the problems with errors in recognition might be much higher. Only the ".en" versions are English-only (such as tiny.en oder small.en).

The "Quick start" section of the page at https://github.com/ggerganov/whisper.cpp will give you the kind of tutorial in text form that you might be looking for.

Thank you. yeah it doesn't accurate completely in this language.
where does this model saved models in my computer? i downloaded 2.8 gb large model and i want to know where it stored.

[KitaitiMakoto]

The model file is in ./models directory if you downloaded it using ./models/download-ggml-model.sh.