up

app.py

@@ -3,230 +3,76 @@ import json
 import pandas as pd
 from tqdm.auto import tqdm
 import streamlit as st
+from pandas import read_csv
+import os
 from huggingface_hub import HfApi, hf_hub_download
 from huggingface_hub.repocard import metadata_load
+import jiwer
 import datetime
+from huggingface_hub import Repository
 
+REFERENCE_NAME = "references"
+SUBMISSION_NAME = "submissions"
 
+REFERENCE_URL = os.path.join("https://huggingface.co/datasets/esc-bench", REFERENCE_NAME)
+SUBMISSION_URL = os.path.join("https://huggingface.co/datasets/esc-bench", SUBMISSION_NAME)
 
-today = datetime.date.today()
-year, week, _ = today.isocalendar()
-
-
-def make_clickable(model_name):
-    link = "https://huggingface.co/" + model_name
-    return f'<a target="_blank" href="{link}">{model_name}</a>'
-
-
-def get_model_ids():
-    api = HfApi()
-    models = api.list_models(filter="esc-bench")
-    model_ids = [x.modelId for x in models]
-    return model_ids
-
-
-def get_metadata(model_id):
-    try:
-        readme_path = hf_hub_download(model_id, filename="README.md")
-        return metadata_load(readme_path)
-    except:
-        # 404 README.md not found
-        print(f"Model id: {model_id} is not great!")
-        return None
-    
-
-
-def parse_metric_value(value):
-    if isinstance(value, str):
-        "".join(value.split("%"))
-        try:
-            value = float(value)
-        except:  # noqa: E722
-            value = None
-    elif isinstance(value, float) and value < 1.1:
-        # assuming that WER is given in 0.xx format
-        value = 100 * value
-    elif isinstance(value, list):
-        if len(value) > 0:
-            value = value[0]
-        else:
-            value = None
-    value = round(value, 2) if value is not None else None
-    return value
-
-
-def parse_metrics_rows(meta):
-    if "model-index" not in meta or "language" not in meta:
-        return None
-    for result in meta["model-index"][0]["results"]:
-        if "dataset" not in result or "metrics" not in result:
-            continue
-        dataset = result["dataset"]["type"]
-        if "args" in result["dataset"] and "language" in result["dataset"]["args"]:
-            lang = result["dataset"]["args"]["language"]
-        else:
-            lang = meta["language"]
-            lang = lang[0] if isinstance(lang, list) else lang
-        lang = aliases_lang[lang] if lang in aliases_lang else lang
-        config = result["dataset"]["config"] if "config" in result["dataset"] else lang
-        split = result["dataset"]["split"] if "split" in result["dataset"] else None
-        row = {
-            "dataset": dataset,
-            "lang": lang,
-            "config": config,
-            "split": split
-        }
-        for metric in result["metrics"]:
-            type = metric["type"].lower().strip()
-            if type not in ["wer", "cer"]:
-                continue
-            value = parse_metric_value(metric["value"])
-            if value is None:
-                continue
-            if type not in row or value < row[type]:
-                # overwrite the metric if the new value is lower (e.g. with LM)
-                row[type] = value
-        if "wer" in row or "cer" in row:
-            yield row
-
-
-@st.cache(ttl=600)
-def get_data():
-    data = []
-    model_ids = get_model_ids()
-    for model_id in tqdm(model_ids):
-        meta = get_metadata(model_id)
-        if meta is None:
-            continue
-        for row in parse_metrics_rows(meta):
-            if row is None:
-                continue
-            row["model_id"] = model_id
-            data.append(row)
-    return pd.DataFrame.from_records(data)
-
-
-def sort_datasets(datasets):
-    # 1. sort by name
-    datasets = sorted(datasets)
-    # 2. bring the suggested datasets to the top and append the rest
-    datasets = sorted(
-        datasets,
-        key=lambda dataset_id: suggested_datasets.index(dataset_id)
-        if dataset_id in suggested_datasets
-        else len(suggested_datasets),
-    )
-    return datasets
-
-
-@st.cache(ttl=600)
-def generate_dataset_info(datasets):
-    msg = """
-    The models have been trained and/or evaluated on the following datasets:
-    """
-    for dataset_id in datasets:
-        if dataset_id in suggested_datasets:
-            msg += f"* [{dataset_id}](https://hf.co/datasets/{dataset_id}) *(recommended)*\n"
-        else:
-            msg += f"* [{dataset_id}](https://hf.co/datasets/{dataset_id})\n"
-
-    msg = "\n".join([line.strip() for line in msg.split("\n")])
-    return msg
-
-
-dataframe = get_data()
-dataframe = dataframe.fillna("")
-
-st.sidebar.image("logo.png", width=200)
-
-st.markdown("# The 🤗 Speech Bench")
-
-st.markdown(
-    f"This is a leaderboard of **{dataframe['model_id'].nunique()}** speech recognition models "
-    f"and **{dataframe['dataset'].nunique()}** datasets.\n\n"
-    "⬅ Please select the language you want to find a model for from the dropdown on the left."
-)
-
-lang = st.sidebar.selectbox(
-    "Language",
-    sorted(dataframe["lang"].unique(), key=lambda key: lang2name.get(key, key)),
-    format_func=lambda key: lang2name.get(key, key),
-    index=0,
-)
-lang_df = dataframe[dataframe.lang == lang]
-
-sorted_datasets = sort_datasets(lang_df["dataset"].unique())
-
-lang_name = lang2name[lang] if lang in lang2name else ""
-num_models = len(lang_df["model_id"].unique())
-num_datasets = len(lang_df["dataset"].unique())
-text = f"""
-For the `{lang}` ({lang_name}) language, there are currently `{num_models}` model(s) 
-trained on `{num_datasets}` dataset(s) available for `automatic-speech-recognition`.
-"""
-st.markdown(text)
-
-st.sidebar.markdown("""
-Choose the dataset that is most relevant to your task and select it from the dropdown below:
-""")
-
-dataset = st.sidebar.selectbox(
-    "Dataset",
-    sorted_datasets,
-    index=0,
-)
-dataset_df = lang_df[lang_df.dataset == dataset]
-
-text = generate_dataset_info(sorted_datasets)
-st.sidebar.markdown(text)
-
-# sort by WER or CER depending on the language
-metric_col = "cer" if lang in cer_langs else "wer"
-if dataset_df["config"].nunique() > 1:
-    # if there are more than one dataset config
-    dataset_df = dataset_df[["model_id", "config", metric_col]]
-    dataset_df = dataset_df.pivot_table(index=['model_id'], columns=["config"], values=[metric_col])
-    dataset_df = dataset_df.reset_index(level=0)
-else:
-    dataset_df = dataset_df[["model_id", metric_col]]
-dataset_df.sort_values(dataset_df.columns[-1], inplace=True)
-dataset_df = dataset_df.fillna("")
-
-dataset_df.rename(
-    columns={
-        "model_id": "Model",
-        "wer": "WER (lower is better)",
-        "cer": "CER (lower is better)",
-    },
-    inplace=True,
-)
-
-st.markdown(
-    "Please click on the model's name to be redirected to its model card which includes documentation and examples on how to use it."
-)
-
-# display the model ranks
-dataset_df = dataset_df.reset_index(drop=True)
-dataset_df.index += 1
-
-# turn the model ids into clickable links
-dataset_df["Model"] = dataset_df["Model"].apply(make_clickable)
-
-table_html = dataset_df.to_html(escape=False)
-table_html = table_html.replace("<th>", '<th align="left">')  # left-align the headers
-st.write(table_html, unsafe_allow_html=True)
-
-if lang in cer_langs:
-    st.markdown(
-        "---\n\* **CER** is [Char Error Rate](https://huggingface.co/metrics/cer)"
-    )
-else:
-    st.markdown(
-        "---\n\* **WER** is [Word Error Rate](https://huggingface.co/metrics/wer)"
-    )
-
-st.markdown(
-    "Want to beat the Leaderboard? Don't see your speech recognition model show up here? "
-    "Simply add the `hf-asr-leaderboard` tag to your model card alongside your evaluation metrics. "
-    "Try our [Metrics Editor](https://huggingface.co/spaces/huggingface/speech-bench-metrics-editor) to get started!"
-)
+TEST_SETS = ["librispeech-clean", "librispeech-other", "common-voice-9", "vox-populi", "ted-lium", "giga-speech", "spgi-speech", "earnings-22", "ami"]
+EXPECTED_TEST_FILES = [f + ".txt" for f in TEST_SETS]
+OPTIONAL_TEST_SETS = ["switch-board", "call-home", "chime-4"]
+
+CSV_RESULTS_FILE = os.path.join(SUBMISSION_NAME, "results.csv")
+
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+
+
+def compute_wer(pred_file, ref_file):
+    with open(pred_file, "r", encoding="utf-8") as pred, open(ref_file, "r", encoding="utf-8") as ref:
+        pred_lines = [line.strip() for line in pred.readlines()]
+        ref_lines = [line.strip() for line in ref.readlines()]
+
+    wer = jiwer.wer(ref_lines, pred_lines)
+    return wer
+
+
+reference_repo = Repository(local_dir="references", clone_from=REFERENCE_URL, use_auth_token=HF_TOKEN)
+submission_repo = Repository(local_dir="submissions", clone_from=SUBMISSION_URL, use_auth_token=HF_TOKEN)
+
+all_submissions = [folder for folder in os.listdir(SUBMISSION_NAME) if os.path.isdir(os.path.join(SUBMISSION_NAME, folder)) and folder != ".git"]
+
+all_results = read_csv(CSV_RESULTS_FILE)
+evaluated_submissions = all_results["name"].values.tolist()
+
+non_evaluated_submissions = set(all_submissions) - set(evaluated_submissions)
+if len(non_evaluated_submissions) > 0:
+    for submission in non_evaluated_submissions:
+        print(f"Evaluate {submission}")
+        results = {"name": submission}
+        submitted_files = os.listdir(os.path.join(SUBMISSION_NAME, submission))
+
+        submitted_files = [f for f in submitted_files if f in EXPECTED_TEST_FILES]
+
+        if sorted(EXPECTED_TEST_FILES) != sorted(submitted_files):
+            raise ValueError(f"{', '.join(submitted_files)} were submitted, but expected {', '.join(EXPECTED_TEST_FILES)}")
+
+        for file in submitted_files:
+            ref_file = os.path.join(REFERENCE_NAME, file)
+            pred_file = os.path.join(SUBMISSION_NAME, submission, file)
+
+            wer = compute_wer(pred_file, ref_file)
+            results[file.split(".")[0]] = str(wer)
+
+        wer_values = [float(results[t]) for t in TEST_SETS]
+        all_wer = sum(wer_values) / len(wer_values)
+
+        results["esc-score"] = all_wer
+        all_results = all_results.append(results, ignore_index=True)
+
+    # save and upload new evaluated results
+    all_results.to_csv(CSV_RESULTS_FILE)
+
+    commit_url = reference_repo.push_to_hub()
+    print(commit_url)
+
+st.table(all_results)

languages.json

@@ -1,982 +0,0 @@
-{
-    "aa": "Afar",
-    "ab": "Abkhazian",
-    "ace": "Achinese",
-    "ady": "Adyghe",
-    "af": "Afrikaans",
-    "af-NA": "Afrikaans (Namibia)",
-    "af-ZA": "Afrikaans (South Africa)",
-    "agq": "Aghem",
-    "agq-CM": "Aghem (Cameroon)",
-    "ak": "Akan",
-    "ak-GH": "Akan (Ghana)",
-    "als": "Tosk Albanian",
-    "am": "Amharic",
-    "am-ET": "Amharic (Ethiopia)",
-    "an": "Aragonese",
-    "ang": "English, Old (ca.450–1100)",
-    "ar": "Arabic",
-    "ar-001": "Arabic (World)",
-    "ar-AE": "Arabic (United Arab Emirates)",
-    "ar-BH": "Arabic (Bahrain)",
-    "ar-DJ": "Arabic (Djibouti)",
-    "ar-DZ": "Arabic (Algeria)",
-    "ar-EG": "Arabic (Egypt)",
-    "ar-EH": "Arabic (Western Sahara)",
-    "ar-ER": "Arabic (Eritrea)",
-    "ar-IL": "Arabic (Israel)",
-    "ar-IQ": "Arabic (Iraq)",
-    "ar-JO": "Arabic (Jordan)",
-    "ar-KM": "Arabic (Comoros)",
-    "ar-KW": "Arabic (Kuwait)",
-    "ar-LB": "Arabic (Lebanon)",
-    "ar-LY": "Arabic (Libya)",
-    "ar-MA": "Arabic (Morocco)",
-    "ar-MR": "Arabic (Mauritania)",
-    "ar-OM": "Arabic (Oman)",
-    "ar-PS": "Arabic (Palestinian Territories)",
-    "ar-QA": "Arabic (Qatar)",
-    "ar-SA": "Arabic (Saudi Arabia)",
-    "ar-SD": "Arabic (Sudan)",
-    "ar-SO": "Arabic (Somalia)",
-    "ar-SS": "Arabic (South Sudan)",
-    "ar-SY": "Arabic (Syria)",
-    "ar-TD": "Arabic (Chad)",
-    "ar-TN": "Arabic (Tunisia)",
-    "ar-YE": "Arabic (Yemen)",
-    "arc": "Official Aramaic (700–300 BCE); Imperial Aramaic (700–300 BCE)",
-    "arz": "Egyptian Arabic",
-    "as": "Assamese",
-    "as-IN": "Assamese (India)",
-    "asa": "Asu",
-    "asa-TZ": "Asu (Tanzania)",
-    "ast": "Asturian",
-    "ast-ES": "Asturian (Spain)",
-    "atj": "Atikamekw",
-    "av": "Avaric",
-    "ay": "Aymara",
-    "az": "Azerbaijani",
-    "az-Cyrl": "Azerbaijani (Cyrillic)",
-    "az-Cyrl-AZ": "Azerbaijani (Cyrillic, Azerbaijan)",
-    "az-Latn": "Azerbaijani (Latin)",
-    "az-Latn-AZ": "Azerbaijani (Latin, Azerbaijan)",
-    "azb": "South Azerbaijani",
-    "ba": "Bashkir",
-    "bar": "Bavarian",
-    "bas": "Basaa",
-    "bas-CM": "Basaa (Cameroon)",
-    "bcl": "Central Bikol",
-    "be": "Belarusian",
-    "be-BY": "Belarusian (Belarus)",
-    "be-tarask": "Belarusan (Taraškievica)",
-    "bem": "Bemba",
-    "bem-ZM": "Bemba (Zambia)",
-    "bez": "Bena",
-    "bez-TZ": "Bena (Tanzania)",
-    "bg": "Bulgarian",
-    "bg-BG": "Bulgarian (Bulgaria)",
-    "bg-Latn": "Bulgarian (Latin)",
-    "bh": "Bihari languages",
-    "bi": "Bislama",
-    "bjn": "Banjar",
-    "bm": "Bambara",
-    "bm-ML": "Bambara (Mali)",
-    "bn": "Bangla",
-    "bn-BD": "Bangla (Bangladesh)",
-    "bn-IN": "Bangla (India)",
-    "bn-Latn": "Bangla (Latin script)",
-    "bo": "Tibetan",
-    "bo-CN": "Tibetan (China)",
-    "bo-IN": "Tibetan (India)",
-    "bpy": "Bishnupriya",
-    "br": "Breton",
-    "br-FR": "Breton (France)",
-    "brx": "Bodo",
-    "brx-IN": "Bodo (India)",
-    "bs": "Bosnian",
-    "bs-Cyrl": "Bosnian (Cyrillic)",
-    "bs-Cyrl-BA": "Bosnian (Cyrillic, Bosnia & Herzegovina)",
-    "bs-Latn": "Bosnian",
-    "bs-Latn-BA": "Bosnian (Bosnia & Herzegovina)",
-    "bug": "Buginese",
-    "bxr": "Russia Buriat",
-    "bzd": "Bribri",
-    "ca": "Catalan",
-    "ca-AD": "Catalan (Andorra)",
-    "ca-ES": "Catalan (Spain)",
-    "ca-ES-valencia": "Catalan (Spain)",
-    "ca-FR": "Catalan (France)",
-    "ca-IT": "Catalan (Italy)",
-    "cbk": "Chavacano",
-    "ccp": "Chakma",
-    "ccp-BD": "Chakma (Bangladesh)",
-    "ccp-IN": "Chakma (India)",
-    "cdo": "Min Dong Chinese",
-    "ce": "Chechen",
-    "ce-RU": "Chechen (Russia)",
-    "ceb": "Cebuano",
-    "ceb-PH": "Cebuano (Philippines)",
-    "cgg": "Chiga",
-    "cgg-UG": "Chiga (Uganda)",
-    "ch": "Chamorro",
-    "cho": "Choctaw",
-    "chr": "Cherokee",
-    "chr-US": "Cherokee (United States)",
-    "chy": "Cheyenne",
-    "ckb": "Central Kurdish",
-    "ckb-IQ": "Central Kurdish (Iraq)",
-    "ckb-IR": "Central Kurdish (Iran)",
-    "cni": "Ashaninka",
-    "cnh": "Hakha Chin",
-    "co": "Corsican",
-    "code": "Programming language (C++, Java, Javascript, Python, etc.)",
-    "cr": "Cree",
-    "crh": "Crimean Tatar; Crimean Turkish",
-    "cs": "Czech",
-    "cs-CZ": "Czech (Czechia)",
-    "csb": "Kashubian",
-    "cu": "Church Slavic",
-    "cu-RU": "Church Slavic (Russia)",
-    "cv": "Chuvash",
-    "cy": "Welsh",
-    "cy-GB": "Welsh (United Kingdom)",
-    "da": "Danish",
-    "da-DK": "Danish (Denmark)",
-    "da-GL": "Danish (Greenland)",
-    "dav": "Taita",
-    "dav-KE": "Taita (Kenya)",
-    "de": "German",
-    "de-AT": "German (Austria)",
-    "de-BE": "German (Belgium)",
-    "de-CH": "German (Switzerland)",
-    "de-DE": "German (Germany)",
-    "de-IT": "German (Italy)",
-    "de-LI": "German (Liechtenstein)",
-    "de-LU": "German (Luxembourg)",
-    "din": "Dinka",
-    "diq": "Dimli (individual language)",
-    "dje": "Zarma",
-    "dje-NE": "Zarma (Niger)",
-    "dsb": "Lower Sorbian",
-    "dsb-DE": "Lower Sorbian (Germany)",
-    "dty": "Doteli",
-    "dua": "Duala",
-    "dua-CM": "Duala (Cameroon)",
-    "dv": "Dhivehi",
-    "dyo": "Jola-Fonyi",
-    "dyo-SN": "Jola-Fonyi (Senegal)",
-    "dz": "Dzongkha",
-    "dz-BT": "Dzongkha (Bhutan)",
-    "ebu": "Embu",
-    "ebu-KE": "Embu (Kenya)",
-    "ee": "Ewe",
-    "ee-GH": "Ewe (Ghana)",
-    "ee-TG": "Ewe (Togo)",
-    "egy": "Egyptian (Ancient)",
-    "el": "Greek",
-    "el-CY": "Greek (Cyprus)",
-    "el-GR": "Greek (Greece)",
-    "el-Latn": "Greek (Latin)",
-    "eml": "Emiliano-Romagnolo",
-    "en": "English",
-    "en-001": "English (World)",
-    "en-150": "English (Europe)",
-    "en-AE": "English (United Arab Emirates)",
-    "en-AG": "English (Antigua & Barbuda)",
-    "en-AI": "English (Anguilla)",
-    "en-AS": "English (American Samoa)",
-    "en-AT": "English (Austria)",
-    "en-AU": "English (Australia)",
-    "en-BB": "English (Barbados)",
-    "en-BE": "English (Belgium)",
-    "en-BI": "English (Burundi)",
-    "en-BM": "English (Bermuda)",
-    "en-BS": "English (Bahamas)",
-    "en-BW": "English (Botswana)",
-    "en-BZ": "English (Belize)",
-    "en-CA": "English (Canada)",
-    "en-CC": "English (Cocos (Keeling) Islands)",
-    "en-CH": "English (Switzerland)",
-    "en-CK": "English (Cook Islands)",
-    "en-CM": "English (Cameroon)",
-    "en-CX": "English (Christmas Island)",
-    "en-CY": "English (Cyprus)",
-    "en-DE": "English (Germany)",
-    "en-DG": "English (Diego Garcia)",
-    "en-DK": "English (Denmark)",
-    "en-DM": "English (Dominica)",
-    "en-ER": "English (Eritrea)",
-    "en-FI": "English (Finland)",
-    "en-FJ": "English (Fiji)",
-    "en-FK": "English (Falkland Islands)",
-    "en-FM": "English (Micronesia)",
-    "en-GB": "English (United Kingdom)",
-    "en-GD": "English (Grenada)",
-    "en-GG": "English (Guernsey)",
-    "en-GH": "English (Ghana)",
-    "en-GI": "English (Gibraltar)",
-    "en-GM": "English (Gambia)",
-    "en-GU": "English (Guam)",
-    "en-GY": "English (Guyana)",
-    "en-HK": "English (Hong Kong SAR China)",
-    "en-IE": "English (Ireland)",
-    "en-IL": "English (Israel)",
-    "en-IM": "English (Isle of Man)",
-    "en-IN": "English (India)",
-    "en-IO": "English (British Indian Ocean Territory)",
-    "en-JE": "English (Jersey)",
-    "en-JM": "English (Jamaica)",
-    "en-KE": "English (Kenya)",
-    "en-KI": "English (Kiribati)",
-    "en-KN": "English (St. Kitts & Nevis)",
-    "en-KY": "English (Cayman Islands)",
-    "en-LC": "English (St. Lucia)",
-    "en-LR": "English (Liberia)",
-    "en-LS": "English (Lesotho)",
-    "en-MG": "English (Madagascar)",
-    "en-MH": "English (Marshall Islands)",
-    "en-MO": "English (Macao SAR China)",
-    "en-MP": "English (Northern Mariana Islands)",
-    "en-MS": "English (Montserrat)",
-    "en-MT": "English (Malta)",
-    "en-MU": "English (Mauritius)",
-    "en-MW": "English (Malawi)",
-    "en-MY": "English (Malaysia)",
-    "en-NA": "English (Namibia)",
-    "en-NF": "English (Norfolk Island)",
-    "en-NG": "English (Nigeria)",
-    "en-NL": "English (Netherlands)",
-    "en-NR": "English (Nauru)",
-    "en-NU": "English (Niue)",
-    "en-NZ": "English (New Zealand)",
-    "en-PG": "English (Papua New Guinea)",
-    "en-PH": "English (Philippines)",
-    "en-PK": "English (Pakistan)",
-    "en-PN": "English (Pitcairn Islands)",
-    "en-PR": "English (Puerto Rico)",
-    "en-PW": "English (Palau)",
-    "en-RW": "English (Rwanda)",
-    "en-SB": "English (Solomon Islands)",
-    "en-SC": "English (Seychelles)",
-    "en-SD": "English (Sudan)",
-    "en-SE": "English (Sweden)",
-    "en-SG": "English (Singapore)",
-    "en-SH": "English (St. Helena)",
-    "en-SI": "English (Slovenia)",
-    "en-SL": "English (Sierra Leone)",
-    "en-SS": "English (South Sudan)",
-    "en-SX": "English (Sint Maarten)",
-    "en-SZ": "English (Eswatini)",
-    "en-TC": "English (Turks & Caicos Islands)",
-    "en-TK": "English (Tokelau)",
-    "en-TO": "English (Tonga)",
-    "en-TT": "English (Trinidad & Tobago)",
-    "en-TV": "English (Tuvalu)",
-    "en-TZ": "English (Tanzania)",
-    "en-UG": "English (Uganda)",
-    "en-UM": "English (U.S. Outlying Islands)",
-    "en-US": "English (United States)",
-    "en-US-posix": "English (United States)",
-    "en-VC": "English (St. Vincent & Grenadines)",
-    "en-VG": "English (British Virgin Islands)",
-    "en-VI": "English (U.S. Virgin Islands)",
-    "en-VU": "English (Vanuatu)",
-    "en-WS": "English (Samoa)",
-    "en-ZA": "English (South Africa)",
-    "en-ZM": "English (Zambia)",
-    "en-ZW": "English (Zimbabwe)",
-    "en-basiceng": "Basic English",
-    "eo": "Esperanto",
-    "eo-001": "Esperanto (World)",
-    "es": "Spanish",
-    "es-419": "Spanish (Latin America)",
-    "es-AR": "Spanish (Argentina)",
-    "es-BO": "Spanish (Bolivia)",
-    "es-BR": "Spanish (Brazil)",
-    "es-BZ": "Spanish (Belize)",
-    "es-CL": "Spanish (Chile)",
-    "es-CO": "Spanish (Colombia)",
-    "es-CR": "Spanish (Costa Rica)",
-    "es-CU": "Spanish (Cuba)",
-    "es-DO": "Spanish (Dominican Republic)",
-    "es-EA": "Spanish (Ceuta & Melilla)",
-    "es-EC": "Spanish (Ecuador)",
-    "es-ES": "Spanish (Spain)",
-    "es-GQ": "Spanish (Equatorial Guinea)",
-    "es-GT": "Spanish (Guatemala)",
-    "es-HN": "Spanish (Honduras)",
-    "es-IC": "Spanish (Canary Islands)",
-    "es-MX": "Spanish (Mexico)",
-    "es-NI": "Spanish (Nicaragua)",
-    "es-PA": "Spanish (Panama)",
-    "es-PE": "Spanish (Peru)",
-    "es-PH": "Spanish (Philippines)",
-    "es-PR": "Spanish (Puerto Rico)",
-    "es-PY": "Spanish (Paraguay)",
-    "es-SV": "Spanish (El Salvador)",
-    "es-US": "Spanish (United States)",
-    "es-UY": "Spanish (Uruguay)",
-    "es-VE": "Spanish (Venezuela)",
-    "et": "Estonian",
-    "et-EE": "Estonian (Estonia)",
-    "eu": "Basque",
-    "eu-ES": "Basque (Spain)",
-    "ewo": "Ewondo",
-    "ewo-CM": "Ewondo (Cameroon)",
-    "ext": "Extremaduran",
-    "fa": "Persian",
-    "fa-AF": "Persian (Afghanistan)",
-    "fa-IR": "Persian (Iran)",
-    "ff": "Fulah",
-    "ff-Adlm": "Fulah (Adlam)",
-    "ff-Adlm-BF": "Fulah (Adlam, Burkina Faso)",
-    "ff-Adlm-CM": "Fulah (Adlam, Cameroon)",
-    "ff-Adlm-GH": "Fulah (Adlam, Ghana)",
-    "ff-Adlm-GM": "Fulah (Adlam, Gambia)",
-    "ff-Adlm-GN": "Fulah (Adlam, Guinea)",
-    "ff-Adlm-GW": "Fulah (Adlam, Guinea-Bissau)",
-    "ff-Adlm-LR": "Fulah (Adlam, Liberia)",
-    "ff-Adlm-MR": "Fulah (Adlam, Mauritania)",
-    "ff-Adlm-NE": "Fulah (Adlam, Niger)",
-    "ff-Adlm-NG": "Fulah (Adlam, Nigeria)",
-    "ff-Adlm-SL": "Fulah (Adlam, Sierra Leone)",
-    "ff-Adlm-SN": "Fulah (Adlam, Senegal)",
-    "ff-Latn": "Fulah (Latin)",
-    "ff-Latn-BF": "Fulah (Latin, Burkina Faso)",
-    "ff-Latn-CM": "Fulah (Latin, Cameroon)",
-    "ff-Latn-GH": "Fulah (Latin, Ghana)",
-    "ff-Latn-GM": "Fulah (Latin, Gambia)",
-    "ff-Latn-GN": "Fulah (Latin, Guinea)",
-    "ff-Latn-GW": "Fulah (Latin, Guinea-Bissau)",
-    "ff-Latn-LR": "Fulah (Latin, Liberia)",
-    "ff-Latn-MR": "Fulah (Latin, Mauritania)",
-    "ff-Latn-NE": "Fulah (Latin, Niger)",
-    "ff-Latn-NG": "Fulah (Latin, Nigeria)",
-    "ff-Latn-SL": "Fulah (Latin, Sierra Leone)",
-    "ff-Latn-SN": "Fulah (Latin, Senegal)",
-    "fi": "Finnish",
-    "fi-FI": "Finnish (Finland)",
-    "fil": "Filipino",
-    "fil-PH": "Filipino (Philippines)",
-    "fj": "Fijian",
-    "fo": "Faroese",
-    "fo-DK": "Faroese (Denmark)",
-    "fo-FO": "Faroese (Faroe Islands)",
-    "fon": "Fon",
-    "fr": "French",
-    "fr-BE": "French (Belgium)",
-    "fr-BF": "French (Burkina Faso)",
-    "fr-BI": "French (Burundi)",
-    "fr-BJ": "French (Benin)",
-    "fr-BL": "French (St. Barthélemy)",
-    "fr-CA": "French (Canada)",
-    "fr-CD": "French (Congo - Kinshasa)",
-    "fr-CF": "French (Central African Republic)",
-    "fr-CG": "French (Congo - Brazzaville)",
-    "fr-CH": "French (Switzerland)",
-    "fr-CI": "French (Côte d’Ivoire)",
-    "fr-CM": "French (Cameroon)",
-    "fr-DJ": "French (Djibouti)",
-    "fr-DZ": "French (Algeria)",
-    "fr-FR": "French (France)",
-    "fr-GA": "French (Gabon)",
-    "fr-GF": "French (French Guiana)",
-    "fr-GN": "French (Guinea)",
-    "fr-GP": "French (Guadeloupe)",
-    "fr-GQ": "French (Equatorial Guinea)",
-    "fr-HT": "French (Haiti)",
-    "fr-KM": "French (Comoros)",
-    "fr-LU": "French (Luxembourg)",
-    "fr-MA": "French (Morocco)",
-    "fr-MC": "French (Monaco)",
-    "fr-MF": "French (St. Martin)",
-    "fr-MG": "French (Madagascar)",
-    "fr-ML": "French (Mali)",
-    "fr-MQ": "French (Martinique)",
-    "fr-MR": "French (Mauritania)",
-    "fr-MU": "French (Mauritius)",
-    "fr-NC": "French (New Caledonia)",
-    "fr-NE": "French (Niger)",
-    "fr-PF": "French (French Polynesia)",
-    "fr-PM": "French (St. Pierre & Miquelon)",
-    "fr-RE": "French (Réunion)",
-    "fr-RW": "French (Rwanda)",
-    "fr-SC": "French (Seychelles)",
-    "fr-SN": "French (Senegal)",
-    "fr-SY": "French (Syria)",
-    "fr-TD": "French (Chad)",
-    "fr-TG": "French (Togo)",
-    "fr-TN": "French (Tunisia)",
-    "fr-VU": "French (Vanuatu)",
-    "fr-WF": "French (Wallis & Futuna)",
-    "fr-YT": "French (Mayotte)",
-    "frp": "Franco-Provençal",
-    "frr": "Northern Frisian",
-    "fur": "Friulian",
-    "fur-IT": "Friulian (Italy)",
-    "fy": "Western Frisian",
-    "fy-NL": "Western Frisian (Netherlands)",
-    "ga": "Irish",
-    "ga-GB": "Irish (United Kingdom)",
-    "ga-IE": "Irish (Ireland)",
-    "gag": "Gagauz",
-    "gan": "Gan Chinese",
-    "gd": "Scottish Gaelic",
-    "gd-GB": "Scottish Gaelic (United Kingdom)",
-    "gl": "Galician",
-    "gl-ES": "Galician (Spain)",
-    "glk": "Gilaki",
-    "gn": "Guarani",
-    "gom": "Goan Konkani",
-    "gor": "Gorontalo",
-    "got": "Gothic",
-    "gsw": "Swiss German",
-    "gsw-CH": "Swiss German (Switzerland)",
-    "gsw-FR": "Swiss German (France)",
-    "gsw-LI": "Swiss German (Liechtenstein)",
-    "gu": "Gujarati",
-    "gu-IN": "Gujarati (India)",
-    "guz": "Gusii",
-    "guz-KE": "Gusii (Kenya)",
-    "gv": "Manx",
-    "gv-IM": "Manx (Isle of Man)",
-    "ha": "Hausa",
-    "ha-GH": "Hausa (Ghana)",
-    "ha-NE": "Hausa (Niger)",
-    "ha-NG": "Hausa (Nigeria)",
-    "hak": "Hakka Chinese",
-    "haw": "Hawaiian",
-    "haw-US": "Hawaiian (United States)",
-    "hch": "Wixarika",
-    "he": "Hebrew",
-    "he-IL": "Hebrew (Israel)",
-    "hi": "Hindi",
-    "hi-IN": "Hindi (India)",
-    "hi-Latn": "Hindi (Latin script)",
-    "hif": "Fiji Hindi",
-    "hmn": "Hmong, Mong",
-    "ho": "Hiri Motu",
-    "hr": "Croatian",
-    "hr-BA": "Croatian (Bosnia & Herzegovina)",
-    "hr-HR": "Croatian (Croatia)",
-    "hsb": "Upper Sorbian",
-    "hsb-DE": "Upper Sorbian (Germany)",
-    "ht": "Haitian",
-    "hu": "Hungarian",
-    "hu-HU": "Hungarian (Hungary)",
-    "hy": "Armenian",
-    "hy-AM": "Armenian (Armenia)",
-    "ia": "Interlingua",
-    "ia-001": "Interlingua (World)",
-    "id": "Indonesian",
-    "id-ID": "Indonesian (Indonesia)",
-    "ie": "Interlingue",
-    "ig": "Igbo",
-    "ig-NG": "Igbo (Nigeria)",
-    "ii": "Sichuan Yi",
-    "ii-CN": "Sichuan Yi (China)",
-    "ik": "Iñupiaq",
-    "ilo": "Iloko",
-    "inh": "Ingush",
-    "io": "Ido",
-    "is": "Icelandic",
-    "is-IS": "Icelandic (Iceland)",
-    "it": "Italian",
-    "it-CH": "Italian (Switzerland)",
-    "it-IT": "Italian (Italy)",
-    "it-SM": "Italian (San Marino)",
-    "it-VA": "Italian (Vatican City)",
-    "iu": "Inuktitut",
-    "iw": "former Hebrew",
-    "ja": "Japanese",
-    "ja-JP": "Japanese (Japan)",
-    "ja-Latn": "Japanese (Latin)",
-    "jam": "Jamaican Patois",
-    "jbo": "Lojban",
-    "jgo": "Ngomba",
-    "jgo-CM": "Ngomba (Cameroon)",
-    "jmc": "Machame",
-    "jmc-TZ": "Machame (Tanzania)",
-    "jv": "Javanese",
-    "jv-ID": "Javanese (Indonesia)",
-    "jv-x-bms": "Banyumasan",
-    "ka": "Georgian",
-    "ka-GE": "Georgian (Georgia)",
-    "kaa": "Karakalpak",
-    "kab": "Kabyle",
-    "kab-DZ": "Kabyle (Algeria)",
-    "kac": "Kachin; Jingpho",
-    "kam": "Kamba",
-    "kam-KE": "Kamba (Kenya)",
-    "kbd": "Kabardian",
-    "kbp": "Kabiye",
-    "kde": "Makonde",
-    "kde-TZ": "Makonde (Tanzania)",
-    "kea": "Kabuverdianu",
-    "kea-CV": "Kabuverdianu (Cape Verde)",
-    "kg": "Kongo",
-    "khq": "Koyra Chiini",
-    "khq-ML": "Koyra Chiini (Mali)",
-    "ki": "Kikuyu",
-    "ki-KE": "Kikuyu (Kenya)",
-    "kj": "Kwanyama",
-    "kk": "Kazakh",
-    "kk-KZ": "Kazakh (Kazakhstan)",
-    "kkj": "Kako",
-    "kkj-CM": "Kako (Cameroon)",
-    "kl": "Kalaallisut",
-    "kl-GL": "Kalaallisut (Greenland)",
-    "kln": "Kalenjin",
-    "kln-KE": "Kalenjin (Kenya)",
-    "km": "Khmer",
-    "km-KH": "Khmer (Cambodia)",
-    "kmr": "Northern Kurdish",
-    "kn": "Kannada",
-    "kn-IN": "Kannada (India)",
-    "ko": "Korean",
-    "ko-KP": "Korean (North Korea)",
-    "ko-KR": "Korean (South Korea)",
-    "koi": "Komi-Permyak",
-    "kok": "Konkani",
-    "kok-IN": "Konkani (India)",
-    "krc": "Karachay-Balkar",
-    "ks": "Kashmiri",
-    "ks-Arab": "Kashmiri (Arabic)",
-    "ks-IN": "Kashmiri (India)",
-    "ksb": "Shambala",
-    "ksb-TZ": "Shambala (Tanzania)",
-    "ksf": "Bafia",
-    "ksf-CM": "Bafia (Cameroon)",
-    "ksh": "Colognian",
-    "ksh-DE": "Colognian (Germany)",
-    "ku": "Kurdish",
-    "ku-TR": "Kurdish (Turkey)",
-    "kv": "Komi",
-    "kw": "Cornish",
-    "kw-GB": "Cornish (United Kingdom)",
-    "ky": "Kyrgyz",
-    "ky-KG": "Kyrgyz (Kyrgyzstan)",
-    "la": "Latin",
-    "lad": "Ladino",
-    "lag": "Langi",
-    "lag-TZ": "Langi (Tanzania)",
-    "lb": "Luxembourgish",
-    "lb-LU": "Luxembourgish (Luxembourg)",
-    "lbe": "Lak",
-    "lez": "Lezghian",
-    "lfn": "Lingua Franca Nova",
-    "lg": "Luganda",
-    "lg-UG": "Ganda (Uganda)",
-    "li": "Limburgan",
-    "lij": "Ligurian",
-    "lkt": "Lakota",
-    "lkt-US": "Lakota (United States)",
-    "lmo": "Lombard",
-    "ln": "Lingala",
-    "ln-AO": "Lingala (Angola)",
-    "ln-CD": "Lingala (Congo - Kinshasa)",
-    "ln-CF": "Lingala (Central African Republic)",
-    "ln-CG": "Lingala (Congo - Brazzaville)",
-    "lo": "Lao",
-    "lo-LA": "Lao (Laos)",
-    "lrc": "Northern Luri",
-    "lrc-IQ": "Northern Luri (Iraq)",
-    "lrc-IR": "Northern Luri (Iran)",
-    "lt": "Lithuanian",
-    "lt-LT": "Lithuanian (Lithuania)",
-    "ltg": "Latgalian",
-    "lu": "Luba-Katanga",
-    "lu-CD": "Luba-Katanga (Congo - Kinshasa)",
-    "luo": "Luo (Kenya and Tanzania)",
-    "luo-KE": "Luo (Kenya and Tanzania) (Kenya)",
-    "luy": "Luyia",
-    "luy-KE": "Luyia (Kenya)",
-    "lv": "Latvian",
-    "lv-LV": "Latvian (Latvia)",
-    "lzh": "Literary Chinese",
-    "mai": "Maithili",
-    "mai-IN": "Maithili (India)",
-    "mas": "Masai",
-    "mas-KE": "Masai (Kenya)",
-    "mas-TZ": "Masai (Tanzania)",
-    "mdf": "Moksha",
-    "mer": "Meru",
-    "mer-KE": "Meru (Kenya)",
-    "mfe": "Morisyen",
-    "mfe-MU": "Morisyen (Mauritius)",
-    "mg": "Malagasy",
-    "mg-MG": "Malagasy (Madagascar)",
-    "mgh": "Makhuwa-Meetto",
-    "mgh-MZ": "Makhuwa-Meetto (Mozambique)",
-    "mgo": "Metaʼ",
-    "mgo-CM": "Metaʼ (Cameroon)",
-    "mh": "Marshallese",
-    "mhr": "Eastern Mari",
-    "mi": "Maori",
-    "mi-NZ": "Maori (New Zealand)",
-    "min": "Minangkabau",
-    "mk": "Macedonian",
-    "mk-MK": "Macedonian (North Macedonia)",
-    "ml": "Malayalam",
-    "ml-IN": "Malayalam (India)",
-    "mn": "Mongolian",
-    "mn-MN": "Mongolian (Mongolia)",
-    "mni": "Manipuri",
-    "mni-Beng": "Manipuri (Bangla)",
-    "mni-Beng-IN": "Manipuri (Bangla, India)",
-    "mr": "Marathi",
-    "mr-IN": "Marathi (India)",
-    "mrj": "Western Mari",
-    "ms": "Malay",
-    "ms-BN": "Malay (Brunei)",
-    "ms-ID": "Malay (Indonesia)",
-    "ms-MY": "Malay (Malaysia)",
-    "ms-SG": "Malay (Singapore)",
-    "mt": "Maltese",
-    "mt-MT": "Maltese (Malta)",
-    "mua": "Mundang",
-    "mua-CM": "Mundang (Cameroon)",
-    "mus": "Muscogee",
-    "mwl": "Mirandese",
-    "my": "Burmese",
-    "my-MM": "Burmese (Myanmar (Burma))",
-    "my-x-zawgyi": "Myanmar (Zawgyi)",
-    "myv": "Erzya",
-    "mzn": "Mazanderani",
-    "mzn-IR": "Mazanderani (Iran)",
-    "na": "Nauruan",
-    "nah": "Nahuatl languages",
-    "nan": "Min Nan Chinese",
-    "nap": "Neapolitan",
-    "naq": "Nama",
-    "naq-NA": "Nama (Namibia)",
-    "nb": "Norwegian Bokmål",
-    "nb-NO": "Norwegian Bokmål (Norway)",
-    "nb-SJ": "Norwegian Bokmål (Svalbard & Jan Mayen)",
-    "nd": "North Ndebele",
-    "nd-ZW": "North Ndebele (Zimbabwe)",
-    "nds": "Low German",
-    "nds-DE": "Low German (Germany)",
-    "nds-NL": "Low German (Netherlands)",
-    "nds-nl": "Dutch Low Saxon",
-    "ne": "Nepali",
-    "ne-IN": "Nepali (India)",
-    "ne-NP": "Nepali (Nepal)",
-    "new": "Newari",
-    "ng": "Ndonga",
-    "nl": "Dutch",
-    "nl-AW": "Dutch (Aruba)",
-    "nl-BE": "Dutch (Belgium)",
-    "nl-BQ": "Dutch (Caribbean Netherlands)",
-    "nl-CW": "Dutch (Curaçao)",
-    "nl-NL": "Dutch (Netherlands)",
-    "nl-SR": "Dutch (Suriname)",
-    "nl-SX": "Dutch (Sint Maarten)",
-    "nmg": "Kwasio",
-    "nmg-CM": "Kwasio (Cameroon)",
-    "nn": "Norwegian Nynorsk",
-    "nn-NO": "Norwegian Nynorsk (Norway)",
-    "nnh": "Ngiemboon",
-    "nnh-CM": "Ngiemboon (Cameroon)",
-    "no": "Norwegian",
-    "nov": "Novial",
-    "nrf": "Norman",
-    "ns": "Northern Sotho",
-    "nso": "Pedi; Sepedi; Northern Sotho",
-    "nus": "Nuer",
-    "nus-SS": "Nuer (South Sudan)",
-    "nv": "Navajo",
-    "ny": "Nyanja",
-    "nyn": "Nyankole",
-    "nyn-UG": "Nyankole (Uganda)",
-    "oc": "Occitan (post 1500)",
-    "olo": "Livvi-Karelian",
-    "om": "Oromo",
-    "om-ET": "Oromo (Ethiopia)",
-    "om-KE": "Oromo (Kenya)",
-    "or": "Odia",
-    "or-IN": "Odia (India)",
-    "os": "Ossetic",
-    "os-GE": "Ossetic (Georgia)",
-    "os-RU": "Ossetic (Russia)",
-    "oto": "Otomi",
-    "pa": "Punjabi",
-    "pa-Arab": "Punjabi (Arabic)",
-    "pa-Arab-PK": "Punjabi (Arabic, Pakistan)",
-    "pa-Guru": "Punjabi",
-    "pa-Guru-IN": "Punjabi (India)",
-    "pa-IN": "Punjabi (India)",
-    "pag": "Pangasinan",
-    "pam": "Pampanga",
-    "pap": "Papiamento",
-    "pcd": "Picard",
-    "pcm": "Nigerian Pidgin",
-    "pcm-NG": "Nigerian Pidgin (Nigeria)",
-    "pdc": "Pennsylvania German",
-    "pfl": "Palatine German",
-    "pi": "Pali",
-    "pih": "Norfolk",
-    "pl": "Polish",
-    "pl-PL": "Polish (Poland)",
-    "pms": "Piemontese",
-    "pnb": "Western Panjabi",
-    "pnt": "Pontic Greek",
-    "prg": "Prussian",
-    "prg-001": "Prussian (World)",
-    "ps": "Pashto",
-    "ps-AF": "Pashto (Afghanistan)",
-    "ps-PK": "Pashto (Pakistan)",
-    "pt": "Portuguese",
-    "pt-AO": "Portuguese (Angola)",
-    "pt-BR": "Portuguese (Brazil)",
-    "pt-CH": "Portuguese (Switzerland)",
-    "pt-CV": "Portuguese (Cape Verde)",
-    "pt-GQ": "Portuguese (Equatorial Guinea)",
-    "pt-GW": "Portuguese (Guinea-Bissau)",
-    "pt-LU": "Portuguese (Luxembourg)",
-    "pt-MO": "Portuguese (Macao SAR China)",
-    "pt-MZ": "Portuguese (Mozambique)",
-    "pt-PT": "Portuguese (Portugal)",
-    "pt-ST": "Portuguese (São Tomé & Príncipe)",
-    "pt-TL": "Portuguese (Timor-Leste)",
-    "qu": "Quechua",
-    "qu-BO": "Quechua (Bolivia)",
-    "qu-EC": "Quechua (Ecuador)",
-    "qu-PE": "Quechua (Peru)",
-    "rm": "Romansh",
-    "rm-CH": "Romansh (Switzerland)",
-    "rm-sursilv": "Romansh (Sursilvan idiom, Switzerland)",
-    "rm-vallader": "Romansh (Vallader idiom, Swizterland)",
-    "rmy": "Vlax Romani",
-    "rn": "Rundi",
-    "rn-BI": "Rundi (Burundi)",
-    "ro": "Romanian",
-    "ro-MD": "Romanian (Moldova)",
-    "ro-RO": "Romanian (Romania)",
-    "rof": "Rombo",
-    "rof-TZ": "Rombo (Tanzania)",
-    "ru": "Russian",
-    "ru-BY": "Russian (Belarus)",
-    "ru-KG": "Russian (Kyrgyzstan)",
-    "ru-KZ": "Russian (Kazakhstan)",
-    "ru-Latn": "Russian (Latin)",
-    "ru-MD": "Russian (Moldova)",
-    "ru-RU": "Russian (Russia)",
-    "ru-UA": "Russian (Ukraine)",
-    "rue": "Rusyn",
-    "rup": "Aromanian",
-    "rw": "Kinyarwanda",
-    "rw-RW": "Kinyarwanda (Rwanda)",
-    "rwk": "Rwa",
-    "rwk-TZ": "Rwa (Tanzania)",
-    "sa": "Sanskrit",
-    "sah": "Sakha",
-    "sah-RU": "Sakha (Russia)",
-    "saq": "Samburu",
-    "saq-KE": "Samburu (Kenya)",
-    "sat": "Santali",
-    "sat-Olck": "Santali (Ol Chiki)",
-    "sat-Olck-IN": "Santali (Ol Chiki, India)",
-    "sbp": "Sangu",
-    "sbp-TZ": "Sangu (Tanzania)",
-    "sc": "Sardinian",
-    "scn": "Sicilian",
-    "sco": "Scots",
-    "sd": "Sindhi",
-    "sd-Arab": "Sindhi (Arabic)",
-    "sd-Arab-PK": "Sindhi (Arabic, Pakistan)",
-    "sd-Deva": "Sindhi (Devanagari)",
-    "sd-Deva-IN": "Sindhi (Devanagari, India)",
-    "se": "Northern Sami",
-    "se-FI": "Northern Sami (Finland)",
-    "se-NO": "Northern Sami (Norway)",
-    "se-SE": "Northern Sami (Sweden)",
-    "seh": "Sena",
-    "seh-MZ": "Sena (Mozambique)",
-    "ses": "Koyraboro Senni",
-    "ses-ML": "Koyraboro Senni (Mali)",
-    "sg": "Sango",
-    "sg-CF": "Sango (Central African Republic)",
-    "sgs": "Samogitian",
-    "sh": "Serbo-Croatian",
-    "shi": "Tachelhit",
-    "shi-Latn": "Tachelhit (Latin)",
-    "shi-Latn-MA": "Tachelhit (Latin, Morocco)",
-    "shi-Tfng": "Tachelhit (Tifinagh)",
-    "shi-Tfng-MA": "Tachelhit (Tifinagh, Morocco)",
-    "shn": "Shan",
-    "shp": "Shipibo-Konibo",
-    "si": "Sinhala",
-    "si-LK": "Sinhala (Sri Lanka)",
-    "simple": "en",
-    "sk": "Slovak",
-    "sk-SK": "Slovak (Slovakia)",
-    "sl": "Slovenian",
-    "sl-SI": "Slovenian (Slovenia)",
-    "sm": "San Marino",
-    "smn": "Inari Sami",
-    "smn-FI": "Inari Sami (Finland)",
-    "sn": "Shona",
-    "sn-ZW": "Shona (Zimbabwe)",
-    "so": "Somali",
-    "so-DJ": "Somali (Djibouti)",
-    "so-ET": "Somali (Ethiopia)",
-    "so-KE": "Somali (Kenya)",
-    "so-SO": "Somali (Somalia)",
-    "sq": "Albanian",
-    "sq-AL": "Albanian (Albania)",
-    "sq-MK": "Albanian (North Macedonia)",
-    "sq-XK": "Albanian (Kosovo)",
-    "sr": "Serbian",
-    "sr-Cyrl": "Serbian (Cyrillic)",
-    "sr-Cyrl-BA": "Serbian (Cyrillic, Bosnia & Herzegovina)",
-    "sr-Cyrl-ME": "Serbian (Cyrillic, Montenegro)",
-    "sr-Cyrl-RS": "Serbian (Cyrillic, Serbia)",
-    "sr-Cyrl-XK": "Serbian (Cyrillic, Kosovo)",
-    "sr-Latn": "Serbian (Latin)",
-    "sr-Latn-BA": "Serbian (Latin, Bosnia & Herzegovina)",
-    "sr-Latn-ME": "Serbian (Latin, Montenegro)",
-    "sr-Latn-RS": "Serbian (Latin, Serbia)",
-    "sr-Latn-XK": "Serbian (Latin, Kosovo)",
-    "srn": "Sranan Tongo",
-    "ss": "Swati",
-    "st": "Southern Sotho",
-    "stq": "Saterland Frisian",
-    "su": "Sundanese",
-    "su-Latn": "Sundanese (Latin)",
-    "su-Latn-ID": "Sundanese (Latin, Indonesia)",
-    "sv": "Swedish",
-    "sv-AX": "Swedish (Åland Islands)",
-    "sv-FI": "Swedish (Finland)",
-    "sv-SE": "Swedish (Sweden)",
-    "sw": "Swahili",
-    "sw-CD": "Swahili (Congo - Kinshasa)",
-    "sw-KE": "Swahili (Kenya)",
-    "sw-TZ": "Swahili (Tanzania)",
-    "sw-UG": "Swahili (Uganda)",
-    "syc": "Syriac",
-    "szl": "Silesian",
-    "ta": "Tamil",
-    "ta-IN": "Tamil (India)",
-    "ta-LK": "Tamil (Sri Lanka)",
-    "ta-Latn": "Tamil (Latin script)",
-    "ta-MY": "Tamil (Malaysia)",
-    "ta-SG": "Tamil (Singapore)",
-    "tar": "Raramuri",
-    "tcy": "Tulu",
-    "tdt": "Tetum",
-    "te": "Telugu",
-    "te-IN": "Telugu (India)",
-    "te-Latn": "Telugu (Latin script)",
-    "teo": "Teso",
-    "teo-KE": "Teso (Kenya)",
-    "teo-UG": "Teso (Uganda)",
-    "tg": "Tajik",
-    "tg-TJ": "Tajik (Tajikistan)",
-    "th": "Thai",
-    "th-TH": "Thai (Thailand)",
-    "ti": "Tigrinya",
-    "ti-ER": "Tigrinya (Eritrea)",
-    "ti-ET": "Tigrinya (Ethiopia)",
-    "tk": "Turkmen",
-    "tk-TM": "Turkmen (Turkmenistan)",
-    "tl": "Tagalog",
-    "tn": "Tswana",
-    "to": "Tongan",
-    "to-TO": "Tongan (Tonga)",
-    "tpi": "Tok Pisin",
-    "tr": "Turkish",
-    "tr-CY": "Turkish (Cyprus)",
-    "tr-TR": "Turkish (Turkey)",
-    "ts": "Tsonga",
-    "tt": "Tatar",
-    "tt-RU": "Tatar (Russia)",
-    "tum": "Tumbuka",
-    "tw": "Twi",
-    "twq": "Tasawaq",
-    "twq-NE": "Tasawaq (Niger)",
-    "ty": "Tahitian",
-    "tyv": "Tuvinian",
-    "tzm": "Central Atlas Tamazight",
-    "tzm-MA": "Central Atlas Tamazight (Morocco)",
-    "udm": "Udmurt",
-    "ug": "Uyghur",
-    "ug-CN": "Uyghur (China)",
-    "uk": "Ukrainian",
-    "uk-UA": "Ukrainian (Ukraine)",
-    "und": "Unknown language",
-    "ur": "Urdu",
-    "ur-IN": "Urdu (India)",
-    "ur-Latn": "Urdu (Latin script)",
-    "ur-PK": "Urdu (Pakistan)",
-    "uz": "Uzbek",
-    "uz-Arab": "Uzbek (Arabic)",
-    "uz-Arab-AF": "Uzbek (Arabic, Afghanistan)",
-    "uz-Cyrl": "Uzbek (Cyrillic)",
-    "uz-Cyrl-UZ": "Uzbek (Cyrillic, Uzbekistan)",
-    "uz-Latn": "Uzbek (Latin)",
-    "uz-Latn-UZ": "Uzbek (Latin, Uzbekistan)",
-    "vai": "Vai",
-    "vai-Latn": "Vai (Latin)",
-    "vai-Latn-LR": "Vai (Latin, Liberia)",
-    "vai-Vaii": "Vai (Vai)",
-    "vai-Vaii-LR": "Vai (Vai, Liberia)",
-    "ve": "Venda",
-    "vec": "Venetian",
-    "vep": "Veps",
-    "vi": "Vietnamese",
-    "vi-VN": "Vietnamese (Vietnam)",
-    "vls": "Vlaams",
-    "vo": "Volapük",
-    "vo-001": "Volapük (World)",
-    "vot": "Votic",
-    "vro": "Võro",
-    "vun": "Vunjo",
-    "vun-TZ": "Vunjo (Tanzania)",
-    "wa": "Walloon",
-    "wae": "Walser",
-    "wae-CH": "Walser (Switzerland)",
-    "war": "Waray (Philippines)",
-    "wo": "Wolof",
-    "wo-SN": "Wolof (Senegal)",
-    "wuu": "Wu Chinese",
-    "xal": "Kalmyk",
-    "xh": "Xhosa",
-    "xh-ZA": "Xhosa (South Africa)",
-    "xmf": "Mingrelian",
-    "xog": "Soga",
-    "xog-UG": "Soga (Uganda)",
-    "yav": "Yangben",
-    "yav-CM": "Yangben (Cameroon)",
-    "yi": "Yiddish",
-    "yi-001": "Yiddish (World)",
-    "yo": "Yoruba",
-    "yo-BJ": "Yoruba (Benin)",
-    "yo-NG": "Yoruba (Nigeria)",
-    "yue": "Cantonese",
-    "yue-Hans": "Cantonese (Simplified)",
-    "yue-Hans-CN": "Cantonese (Simplified, China)",
-    "yue-Hant": "Cantonese (Traditional)",
-    "yue-Hant-HK": "Cantonese (Traditional, Hong Kong SAR China)",
-    "za": "Zhuang",
-    "zea": "Zeeuws",
-    "zgh": "Standard Moroccan Tamazight",
-    "zgh-MA": "Standard Moroccan Tamazight (Morocco)",
-    "zh": "Chinese",
-    "zh-CN": "Chinese (Mandarin, China)",
-    "zh-HK": "Cantonese (Hong Kong)",
-    "zh-Hans": "Chinese (Simplified)",
-    "zh-Hans-CN": "Chinese (Simplified, China)",
-    "zh-Hans-HK": "Chinese (Simplified, Hong Kong SAR China)",
-    "zh-Hans-MO": "Chinese (Simplified, Macao SAR China)",
-    "zh-Hans-SG": "Chinese (Simplified, Singapore)",
-    "zh-Hant": "Chinese (Traditional)",
-    "zh-Hant-HK": "Chinese (Traditional, Hong Kong SAR China)",
-    "zh-Hant-MO": "Chinese (Traditional, Macao SAR China)",
-    "zh-Hant-TW": "Chinese (Traditional, Taiwan)",
-    "zh-Latn": "Chinese (Latin)",
-    "zh-TW": "Chinese (Mandarin, Taiwan)",
-    "zu": "Zulu",
-    "zu-ZA": "Zulu (South Africa)",
-    "zza": "Zaza"
-}

requirements.txt

@@ -0,0 +1,2 @@
+huggingface_hub==0.8.1
+pandas