Fix the language list

app.py

@@ -7,15 +7,15 @@ import torchaudio
 from seamless_communication.models.inference.translator import Translator
 
 from lang_list import (
-    S2ST_TARGET_LANGUAGES,
-    S2TT_TARGET_LANGUAGES,
-    T2TT_TARGET_LANGUAGES,
-    TEXT_SOURCE_LANGUAGES,
+    LANGUAGE_NAME_TO_CODE,
+    S2ST_TARGET_LANGUAGE_NAMES,
+    S2TT_TARGET_LANGUAGE_NAMES,
+    T2TT_TARGET_LANGUAGE_NAMES,
+    TEXT_SOURCE_LANGUAGE_NAMES,
 )
 
 DESCRIPTION = "# SeamlessM4T"
 
-
 TASK_NAMES = [
     "S2ST (Speech to Speech translation)",
     "S2TT (Speech to Text translation)",
@@ -27,6 +27,8 @@ TASK_NAMES = [
 AUDIO_SAMPLE_RATE = 16000.0
 MAX_INPUT_AUDIO_LENGTH = 60  # in seconds
 
+DEFAULT_TARGET_LANGUAGE = "French"
+
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 translator = Translator(
     model_name_or_card="multitask_unity_large",
@@ -46,6 +48,9 @@ def predict(
     target_language: str,
 ) -> tuple[tuple[int, np.ndarray] | None, str]:
     task_name = task_name.split()[0]
+    source_language_code = LANGUAGE_NAME_TO_CODE[source_language]
+    target_language_code = LANGUAGE_NAME_TO_CODE[target_language]
+
     if task_name in ["S2ST", "S2TT", "ASR"]:
         if audio_source == "microphone":
             input_data = input_audio_mic
@@ -64,8 +69,8 @@ def predict(
     text_out, wav, sr = translator.predict(
         input=input_data,
         task_str=task_name,
-        tgt_lang=target_language,
-        src_lang=source_language,
+        tgt_lang=target_language_code,
+        src_lang=source_language_code,
     )
     if task_name in ["S2ST", "T2ST"]:
         return (sr, wav.cpu().detach().numpy()), text_out
@@ -88,35 +93,45 @@ def update_input_ui(task_name: str) -> tuple[dict, dict, dict, dict]:
             gr.update(visible=True),  # audio_box
             gr.update(visible=False),  # input_text
             gr.update(visible=False),  # source_language
-            gr.update(visible=True, choices=S2ST_TARGET_LANGUAGES, value="fra"),  # target_language
+            gr.update(
+                visible=True, choices=S2ST_TARGET_LANGUAGE_NAMES, value=DEFAULT_TARGET_LANGUAGE
+            ),  # target_language
         )
     elif task_name == "S2TT":
         return (
             gr.update(visible=True),  # audio_box
             gr.update(visible=False),  # input_text
             gr.update(visible=False),  # source_language
-            gr.update(visible=True, choices=S2TT_TARGET_LANGUAGES, value="fra"),  # target_language
+            gr.update(
+                visible=True, choices=S2TT_TARGET_LANGUAGE_NAMES, value=DEFAULT_TARGET_LANGUAGE
+            ),  # target_language
         )
     elif task_name == "T2ST":
         return (
             gr.update(visible=False),  # audio_box
             gr.update(visible=True),  # input_text
             gr.update(visible=True),  # source_language
-            gr.update(visible=True, choices=S2ST_TARGET_LANGUAGES, value="fra"),  # target_language
+            gr.update(
+                visible=True, choices=S2ST_TARGET_LANGUAGE_NAMES, value=DEFAULT_TARGET_LANGUAGE
+            ),  # target_language
         )
     elif task_name == "T2TT":
         return (
             gr.update(visible=False),  # audio_box
             gr.update(visible=True),  # input_text
             gr.update(visible=True),  # source_language
-            gr.update(visible=True, choices=T2TT_TARGET_LANGUAGES, value="fra"),  # target_language
+            gr.update(
+                visible=True, choices=T2TT_TARGET_LANGUAGE_NAMES, value=DEFAULT_TARGET_LANGUAGE
+            ),  # target_language
         )
     elif task_name == "ASR":
         return (
             gr.update(visible=True),  # audio_box
             gr.update(visible=False),  # input_text
             gr.update(visible=False),  # source_language
-            gr.update(visible=True, choices=S2TT_TARGET_LANGUAGES, value="fra"),  # target_language
+            gr.update(
+                visible=True, choices=S2TT_TARGET_LANGUAGE_NAMES, value=DEFAULT_TARGET_LANGUAGE
+            ),  # target_language
         )
     else:
         raise ValueError(f"Unknown task: {task_name}")
@@ -154,14 +169,14 @@ with gr.Blocks(css="style.css") as demo:
         with gr.Row():
             source_language = gr.Dropdown(
                 label="Source language",
-                choices=TEXT_SOURCE_LANGUAGES,
-                value="eng",
+                choices=TEXT_SOURCE_LANGUAGE_NAMES,
+                value="English",
                 visible=False,
             )
             target_language = gr.Dropdown(
                 label="Target language",
-                choices=S2ST_TARGET_LANGUAGES,
-                value="fra",
+                choices=S2ST_TARGET_LANGUAGE_NAMES,
+                value=DEFAULT_TARGET_LANGUAGE,
             )
         with gr.Row() as audio_box:
             audio_source = gr.Radio(

lang_list.py

@@ -1,6 +1,113 @@
+# Language dict
+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",
+    "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",
+}
+LANGUAGE_NAME_TO_CODE = {v: k for k, v in language_code_to_name.items()}
+
 # Source langs: S2ST / S2TT / ASR don't need source lang
 # T2TT / T2ST use this
-TEXT_SOURCE_LANGUAGES = [
+text_source_language_codes = [
     "afr",
     "amh",
     "arb",
@@ -17,7 +124,6 @@ TEXT_SOURCE_LANGUAGES = [
     "ces",
     "ckb",
     "cmn",
-    "zho_Hant",
     "cym",
     "dan",
     "deu",
@@ -27,7 +133,6 @@ TEXT_SOURCE_LANGUAGES = [
     "eus",
     "fin",
     "fra",
-    "fuv",
     "gaz",
     "gle",
     "glg",
@@ -75,7 +180,6 @@ TEXT_SOURCE_LANGUAGES = [
     "por",
     "ron",
     "rus",
-    "sat",
     "slk",
     "slv",
     "sna",
@@ -100,10 +204,11 @@ TEXT_SOURCE_LANGUAGES = [
     "zsm",
     "zul",
 ]
+TEXT_SOURCE_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in text_source_language_codes])
 
 # Target langs:
 # S2ST / T2ST
-S2ST_TARGET_LANGUAGES = [
+s2st_target_language_codes = [
     "eng",
     "arb",
     "ben",
@@ -133,94 +238,6 @@ S2ST_TARGET_LANGUAGES = [
     "swe",
     "swh",
     "tel",
-    "tgl/fil",
-    "tha",
-    "tur",
-    "ukr",
-    "urd",
-    "uzn",
-    "vie",
-]
-# S2TT / ASR
-S2TT_TARGET_LANGUAGES = [
-    "amh",
-    "arb",
-    "asm",
-    "azj",
-    "bel",
-    "ben",
-    "bos",
-    "bul",
-    "cat",
-    "ceb",
-    "ces",
-    "ckb",
-    "cmn",
-    "cym",
-    "dan",
-    "deu",
-    "ell",
-    "eng",
-    "est",
-    "fin",
-    "fra",
-    "ful",
-    "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",
-    "mal",
-    "mar",
-    "mkd",
-    "mlt",
-    "mya",
-    "nld",
-    "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",
@@ -228,109 +245,10 @@ S2TT_TARGET_LANGUAGES = [
     "urd",
     "uzn",
     "vie",
-    "yor",
-    "yue",
-    "zlm",
-    "zul",
 ]
+S2ST_TARGET_LANGUAGE_NAMES = sorted([language_code_to_name[code] for code in s2st_target_language_codes])
+
+# S2TT / ASR
+S2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES
 # T2TT
-T2TT_TARGET_LANGUAGES = [
-    "afr",
-    "amh",
-    "arb",
-    "ary",
-    "arz",
-    "asm",
-    "azj",
-    "bel",
-    "ben",
-    "bos",
-    "bul",
-    "cat",
-    "ceb",
-    "ces",
-    "ckb",
-    "cmn",
-    "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",
-    "sat",
-    "slk",
-    "slv",
-    "sna",
-    "snd",
-    "som",
-    "spa",
-    "srp",
-    "swe",
-    "swh",
-    "tam",
-    "tel",
-    "tgk",
-    "tgl",
-    "tha",
-    "tur",
-    "ukr",
-    "urd",
-    "uzn",
-    "vie",
-    "yor",
-    "yue",
-    "zho_Hant",
-    "zsm",
-    "zul",
-]
+T2TT_TARGET_LANGUAGE_NAMES = TEXT_SOURCE_LANGUAGE_NAMES