add audio to audio translation to SeamlessM4T (rsxdalv#284)

* add audio to audio translation to SeamlessM4T

* readme

Author: rsxdalv

README.md

@@ -43,6 +43,7 @@ https://github.com/rsxdalv/tts-generation-webui/discussions/186#discussioncommen
 ## Changelog
 Mar 10:
 * Add Batching to React UI Magnet (#283)
+* Add audio to audio translation to SeamlessM4T (#284)
 
 Mar 5:
 * Add Batching to React UI MusicGen (#281), thanks to https://github.com/Aamir3d for requesting this and providing feedback

src/seamlessM4T/language_code_to_name.py

@@ -0,0 +1,127 @@
+language_code_to_name = {
+    "afr": "Afrikaans",
+    "amh": "Amharic",
+    "arb": "Modern Standard Arabic",
+    "ary": "Moroccan Arabic",
+    "arz": "Egyptian Arabic",
+    "asm": "Assamese",
+    "ast": "Asturian",
+    "azj": "North Azerbaijani",
+    "bel": "Belarusian",
+    "ben": "Bengali",
+    "bos": "Bosnian",
+    "bul": "Bulgarian",
+    "cat": "Catalan",
+    "ceb": "Cebuano",
+    "ces": "Czech",
+    "ckb": "Central Kurdish",
+    "cmn": "Mandarin Chinese",
+    "cmn_Hant": "Traditional Mandarin Chinese",
+    "cym": "Welsh",
+    "dan": "Danish",
+    "deu": "German",
+    "ell": "Greek",
+    "eng": "English",
+    "est": "Estonian",
+    "eus": "Basque",
+    "fin": "Finnish",
+    "fra": "French",
+    "gaz": "West Central Oromo",
+    "gle": "Irish",
+    "glg": "Galician",
+    "guj": "Gujarati",
+    "heb": "Hebrew",
+    "hin": "Hindi",
+    "hrv": "Croatian",
+    "hun": "Hungarian",
+    "hye": "Armenian",
+    "ibo": "Igbo",
+    "ind": "Indonesian",
+    "isl": "Icelandic",
+    "ita": "Italian",
+    "jav": "Javanese",
+    "jpn": "Japanese",
+    "kam": "Kamba",
+    "kan": "Kannada",
+    "kat": "Georgian",
+    "kaz": "Kazakh",
+    "kea": "Kabuverdianu",
+    "khk": "Halh Mongolian",
+    "khm": "Khmer",
+    "kir": "Kyrgyz",
+    "kor": "Korean",
+    "lao": "Lao",
+    "lit": "Lithuanian",
+    "ltz": "Luxembourgish",
+    "lug": "Ganda",
+    "luo": "Luo",
+    "lvs": "Standard Latvian",
+    "mai": "Maithili",
+    "mal": "Malayalam",
+    "mar": "Marathi",
+    "mkd": "Macedonian",
+    "mlt": "Maltese",
+    "mni": "Meitei",
+    "mya": "Burmese",
+    "nld": "Dutch",
+    "nno": "Norwegian Nynorsk",
+    "nob": "Norwegian Bokm\u00e5l",
+    "npi": "Nepali",
+    "nya": "Nyanja",
+    "oci": "Occitan",
+    "ory": "Odia",
+    "pan": "Punjabi",
+    "pbt": "Southern Pashto",
+    "pes": "Western Persian",
+    "pol": "Polish",
+    "por": "Portuguese",
+    "ron": "Romanian",
+    "rus": "Russian",
+    "slk": "Slovak",
+    "slv": "Slovenian",
+    "sna": "Shona",
+    "snd": "Sindhi",
+    "som": "Somali",
+    "spa": "Spanish",
+    "srp": "Serbian",
+    "swe": "Swedish",
+    "swh": "Swahili",
+    "tam": "Tamil",
+    "tel": "Telugu",
+    "tgk": "Tajik",
+    "tgl": "Tagalog",
+    "tha": "Thai",
+    "tur": "Turkish",
+    "ukr": "Ukrainian",
+    "urd": "Urdu",
+    "uzn": "Northern Uzbek",
+    "vie": "Vietnamese",
+    "xho": "Xhosa",
+    "yor": "Yoruba",
+    "yue": "Cantonese",
+    "zlm": "Colloquial Malay",
+    "zsm": "Standard Malay",
+    "zul": "Zulu",
+
+    "fuv": "Nigerian Fulfulde",
+    "gle": "Irish",
+    "sat": "Santali",
+    "pbt": "Southern Pashto",
+    "zsm": "Standard Malay",
+    "xho": "Xhosa",
+    "kea": "Kabuverdianu",
+}
+
+
+def get_language_name(language_code):
+    return language_code_to_name[language_code]
+
+text_source_codes = ["afr","amh","arb","ary","arz","asm","azj","bel","ben","bos","bul","cat","ceb","ces","ckb","cmn","cmn_Hant","cym","dan","deu","ell","eng","est","eus","fin","fra","fuv","gaz","gle","glg","guj","heb","hin","hrv","hun","hye","ibo","ind","isl","ita","jav","jpn","kan","kat","kaz","khk","khm","kir","kor","lao","lit","lug","luo","lvs","mai","mal","mar","mkd","mlt","mni","mya","nld","nno","nob","npi","nya","ory","pan","pbt","pes","pol","por","ron","rus","slk","slv","sna","snd","som","spa","srp","swe","swh","tam","tel","tgk","tgl","tha","tur","ukr","urd","uzn","vie","yor","yue","zsm","zul"]
+text_target_codes = ["afr","amh","arb","ary","arz","asm","azj","bel","ben","bos","bul","cat","ceb","ces","ckb","cmn","cmn_Hant","cym","dan","deu","ell","eng","est","eus","fin","fra","fuv","gaz","gle","glg","guj","heb","hin","hrv","hun","hye","ibo","ind","isl","ita","jav","jpn","kan","kat","kaz","khk","khm","kir","kor","lao","lit","lug","luo","lvs","mai","mal","mar","mkd","mlt","mni","mya","nld","nno","nob","npi","nya","ory","pan","pbt","pes","pol","por","ron","rus","slk","slv","sna","snd","som","spa","srp","swe","swh","tam","tel","tgk","tgl","tha","tur","ukr","urd","uzn","vie","yor","yue","zsm","zul"]
+speech_source_codes = ["afr","amh","arb","ary","arz","asm","ast","azj","bel","ben","bos","bul","cat","ceb","ces","ckb","cmn","cmn_Hant","cym","dan","deu","ell","eng","est","eus","fin","fra","fuv","gaz","gle","glg","guj","heb","hin","hrv","hun","hye","ibo","ind","isl","ita","jav","jpn","kam","kan","kat","kaz","kea","khk","khm","kir","kor","lao","lit","ltz","lug","luo","lvs","mai","mal","mar","mkd","mlt","mni","mya","nld","nno","nob","npi","nya","oci","ory","pan","pbt","pes","pol","por","ron","rus","slk","slv","sna","snd","som","spa","srp","swe","swh","tam","tel","tgk","tgl","tha","tur","ukr","urd","uzn","vie","xho","yor","yue","zlm","zul"]
+speech_target_codes = ["arb","ben","cat","ces","cmn","cmn_Hant","cym","dan","deu","eng","est","fin","fra","hin","ind","ita","jpn","kor","mlt","nld","pes","pol","por","ron","rus","slk","spa","swe","swh","tel","tgl","tha","tur","ukr","urd","uzn","vie"]
+
+text_source_languages = [get_language_name(code) for code in text_source_codes]
+text_target_languages = [get_language_name(code) for code in text_target_codes]
+speech_source_languages = [get_language_name(code) for code in speech_source_codes]
+speech_target_languages = [get_language_name(code) for code in speech_target_codes]