nllb v0

README.md

@@ -39,6 +39,8 @@ Real-time speech transcription directly to your browser, with a ready-to-use bac
 ```bash
 pip install whisperlivekit
 ```
+> You can also clone the repo and `pip install -e .` for the latest version.
+
 
 >  **FFmpeg is required** and must be installed before using WhisperLiveKit
 > 
@@ -148,7 +150,8 @@ The rest I don't recommend. But below are your options.
 |-----------|-------------|---------|
 | `--model` | Whisper model size. | `small` |
 | `--language` | Source language code or `auto` | `auto` |
-| `--task` | `transcribe` or `translate` | `transcribe` |
+| `--task` | Set to `translate` to translate to english | `transcribe` |
+| `--target-language` | [NOT FUNCTIONAL YET] | `None` |
 | `--backend` | Processing backend | `simulstreaming` |
 | `--min-chunk-size` | Minimum audio chunk size (seconds) | `1.0` |
 | `--no-vac` | Disable Voice Activity Controller | `False` |

whisperlivekit/core.py

@@ -33,6 +33,7 @@ class TranscriptionEngine:
             "model_dir": None,
             "lan": "auto",
             "task": "transcribe",
+            "target_language": "",
             "backend": "faster-whisper",
             "vac": True,
             "vac_chunk_size": 0.04,
@@ -133,6 +134,12 @@ class TranscriptionEngine:
             else:
                 raise ValueError(f"Unknown diarization backend: {self.args.diarization_backend}")
             
+        if self.args.target_language:
+            if self.args.language == 'auto':
+                raise Exception('Translation cannot be set with language auto')
+            else:
+                from whisperlivekit.translation.translation import load_model
+            
         TranscriptionEngine._initialized = True
 
 

whisperlivekit/parse_args.py

@@ -112,6 +112,15 @@ def parse_args():
         choices=["transcribe", "translate"],
         help="Transcribe or translate.",
     )
+    
+    parser.add_argument(
+        "--target-language",
+        type=str,
+        default="",
+        dest="target_language",
+        help="Target language for translation. Not functional yet.",
+    )    
+
     parser.add_argument(
         "--backend",
         type=str,

whisperlivekit/translation/mapping_languages.py

@@ -0,0 +1,182 @@
+"""
+adapted from https://store.crowdin.com/custom-mt
+"""
+
+LANGUAGES = [
+    {"name": "Afrikaans", "nllb": "afr_Latn", "crowdin": "af"},
+    {"name": "Akan", "nllb": "aka_Latn", "crowdin": "ak"},
+    {"name": "Amharic", "nllb": "amh_Ethi", "crowdin": "am"},
+    {"name": "Assamese", "nllb": "asm_Beng", "crowdin": "as"},
+    {"name": "Asturian", "nllb": "ast_Latn", "crowdin": "ast"},
+    {"name": "Bashkir", "nllb": "bak_Cyrl", "crowdin": "ba"},
+    {"name": "Bambara", "nllb": "bam_Latn", "crowdin": "bm"},
+    {"name": "Balinese", "nllb": "ban_Latn", "crowdin": "ban"},
+    {"name": "Belarusian", "nllb": "bel_Cyrl", "crowdin": "be"},
+    {"name": "Bengali", "nllb": "ben_Beng", "crowdin": "bn"},
+    {"name": "Bosnian", "nllb": "bos_Latn", "crowdin": "bs"},
+    {"name": "Bulgarian", "nllb": "bul_Cyrl", "crowdin": "bg"},
+    {"name": "Catalan", "nllb": "cat_Latn", "crowdin": "ca"},
+    {"name": "Cebuano", "nllb": "ceb_Latn", "crowdin": "ceb"},
+    {"name": "Czech", "nllb": "ces_Latn", "crowdin": "cs"},
+    {"name": "Welsh", "nllb": "cym_Latn", "crowdin": "cy"},
+    {"name": "Danish", "nllb": "dan_Latn", "crowdin": "da"},
+    {"name": "German", "nllb": "deu_Latn", "crowdin": "de"},
+    {"name": "Dzongkha", "nllb": "dzo_Tibt", "crowdin": "dz"},
+    {"name": "Greek", "nllb": "ell_Grek", "crowdin": "el"},
+    {"name": "English", "nllb": "eng_Latn", "crowdin": "en"},
+    {"name": "Esperanto", "nllb": "epo_Latn", "crowdin": "eo"},
+    {"name": "Estonian", "nllb": "est_Latn", "crowdin": "et"},
+    {"name": "Basque", "nllb": "eus_Latn", "crowdin": "eu"},
+    {"name": "Ewe", "nllb": "ewe_Latn", "crowdin": "ee"},
+    {"name": "Faroese", "nllb": "fao_Latn", "crowdin": "fo"},
+    {"name": "Fijian", "nllb": "fij_Latn", "crowdin": "fj"},
+    {"name": "Finnish", "nllb": "fin_Latn", "crowdin": "fi"},
+    {"name": "French", "nllb": "fra_Latn", "crowdin": "fr"},
+    {"name": "Friulian", "nllb": "fur_Latn", "crowdin": "fur-IT"},
+    {"name": "Scottish Gaelic", "nllb": "gla_Latn", "crowdin": "gd"},
+    {"name": "Irish", "nllb": "gle_Latn", "crowdin": "ga-IE"},
+    {"name": "Galician", "nllb": "glg_Latn", "crowdin": "gl"},
+    {"name": "Guarani", "nllb": "grn_Latn", "crowdin": "gn"},
+    {"name": "Gujarati", "nllb": "guj_Gujr", "crowdin": "gu-IN"},
+    {"name": "Haitian Creole", "nllb": "hat_Latn", "crowdin": "ht"},
+    {"name": "Hausa", "nllb": "hau_Latn", "crowdin": "ha"},
+    {"name": "Hebrew", "nllb": "heb_Hebr", "crowdin": "he"},
+    {"name": "Hindi", "nllb": "hin_Deva", "crowdin": "hi"},
+    {"name": "Croatian", "nllb": "hrv_Latn", "crowdin": "hr"},
+    {"name": "Hungarian", "nllb": "hun_Latn", "crowdin": "hu"},
+    {"name": "Armenian", "nllb": "hye_Armn", "crowdin": "hy-AM"},
+    {"name": "Igbo", "nllb": "ibo_Latn", "crowdin": "ig"},
+    {"name": "Indonesian", "nllb": "ind_Latn", "crowdin": "id"},
+    {"name": "Icelandic", "nllb": "isl_Latn", "crowdin": "is"},
+    {"name": "Italian", "nllb": "ita_Latn", "crowdin": "it"},
+    {"name": "Javanese", "nllb": "jav_Latn", "crowdin": "jv"},
+    {"name": "Japanese", "nllb": "jpn_Jpan", "crowdin": "ja"},
+    {"name": "Kabyle", "nllb": "kab_Latn", "crowdin": "kab"},
+    {"name": "Kannada", "nllb": "kan_Knda", "crowdin": "kn"},
+    {"name": "Georgian", "nllb": "kat_Geor", "crowdin": "ka"},
+    {"name": "Kazakh", "nllb": "kaz_Cyrl", "crowdin": "kk"},
+    {"name": "Khmer", "nllb": "khm_Khmr", "crowdin": "km"},
+    {"name": "Kinyarwanda", "nllb": "kin_Latn", "crowdin": "rw"},
+    {"name": "Kyrgyz", "nllb": "kir_Cyrl", "crowdin": "ky"},
+    {"name": "Korean", "nllb": "kor_Hang", "crowdin": "ko"},
+    {"name": "Lao", "nllb": "lao_Laoo", "crowdin": "lo"},
+    {"name": "Ligurian", "nllb": "lij_Latn", "crowdin": "lij"},
+    {"name": "Limburgish", "nllb": "lim_Latn", "crowdin": "li"},
+    {"name": "Lingala", "nllb": "lin_Latn", "crowdin": "ln"},
+    {"name": "Lithuanian", "nllb": "lit_Latn", "crowdin": "lt"},
+    {"name": "Luxembourgish", "nllb": "ltz_Latn", "crowdin": "lb"},
+    {"name": "Maithili", "nllb": "mai_Deva", "crowdin": "mai"},
+    {"name": "Malayalam", "nllb": "mal_Mlym", "crowdin": "ml-IN"},
+    {"name": "Marathi", "nllb": "mar_Deva", "crowdin": "mr"},
+    {"name": "Macedonian", "nllb": "mkd_Cyrl", "crowdin": "mk"},
+    {"name": "Maltese", "nllb": "mlt_Latn", "crowdin": "mt"},
+    {"name": "Mossi", "nllb": "mos_Latn", "crowdin": "mos"},
+    {"name": "Maori", "nllb": "mri_Latn", "crowdin": "mi"},
+    {"name": "Burmese", "nllb": "mya_Mymr", "crowdin": "my"},
+    {"name": "Dutch", "nllb": "nld_Latn", "crowdin": "nl"},
+    {"name": "Norwegian Nynorsk", "nllb": "nno_Latn", "crowdin": "nn-NO"},
+    {"name": "Nepali", "nllb": "npi_Deva", "crowdin": "ne-NP"},
+    {"name": "Northern Sotho", "nllb": "nso_Latn", "crowdin": "nso"},
+    {"name": "Occitan", "nllb": "oci_Latn", "crowdin": "oc"},
+    {"name": "Odia", "nllb": "ory_Orya", "crowdin": "or"},
+    {"name": "Papiamento", "nllb": "pap_Latn", "crowdin": "pap"},
+    {"name": "Polish", "nllb": "pol_Latn", "crowdin": "pl"},
+    {"name": "Portuguese", "nllb": "por_Latn", "crowdin": "pt-PT"},
+    {"name": "Dari", "nllb": "prs_Arab", "crowdin": "fa-AF"},
+    {"name": "Romanian", "nllb": "ron_Latn", "crowdin": "ro"},
+    {"name": "Rundi", "nllb": "run_Latn", "crowdin": "rn"},
+    {"name": "Russian", "nllb": "rus_Cyrl", "crowdin": "ru"},
+    {"name": "Sango", "nllb": "sag_Latn", "crowdin": "sg"},
+    {"name": "Sanskrit", "nllb": "san_Deva", "crowdin": "sa"},
+    {"name": "Santali", "nllb": "sat_Olck", "crowdin": "sat"},
+    {"name": "Sinhala", "nllb": "sin_Sinh", "crowdin": "si-LK"},
+    {"name": "Slovak", "nllb": "slk_Latn", "crowdin": "sk"},
+    {"name": "Slovenian", "nllb": "slv_Latn", "crowdin": "sl"},
+    {"name": "Shona", "nllb": "sna_Latn", "crowdin": "sn"},
+    {"name": "Sindhi", "nllb": "snd_Arab", "crowdin": "sd"},
+    {"name": "Somali", "nllb": "som_Latn", "crowdin": "so"},
+    {"name": "Southern Sotho", "nllb": "sot_Latn", "crowdin": "st"},
+    {"name": "Spanish", "nllb": "spa_Latn", "crowdin": "es-ES"},
+    {"name": "Sardinian", "nllb": "srd_Latn", "crowdin": "sc"},
+    {"name": "Swati", "nllb": "ssw_Latn", "crowdin": "ss"},
+    {"name": "Sundanese", "nllb": "sun_Latn", "crowdin": "su"},
+    {"name": "Swedish", "nllb": "swe_Latn", "crowdin": "sv-SE"},
+    {"name": "Swahili", "nllb": "swh_Latn", "crowdin": "sw"},
+    {"name": "Tamil", "nllb": "tam_Taml", "crowdin": "ta"},
+    {"name": "Tatar", "nllb": "tat_Cyrl", "crowdin": "tt-RU"},
+    {"name": "Telugu", "nllb": "tel_Telu", "crowdin": "te"},
+    {"name": "Tajik", "nllb": "tgk_Cyrl", "crowdin": "tg"},
+    {"name": "Tagalog", "nllb": "tgl_Latn", "crowdin": "tl"},
+    {"name": "Thai", "nllb": "tha_Thai", "crowdin": "th"},
+    {"name": "Tigrinya", "nllb": "tir_Ethi", "crowdin": "ti"},
+    {"name": "Tswana", "nllb": "tsn_Latn", "crowdin": "tn"},
+    {"name": "Tsonga", "nllb": "tso_Latn", "crowdin": "ts"},
+    {"name": "Turkmen", "nllb": "tuk_Latn", "crowdin": "tk"},
+    {"name": "Turkish", "nllb": "tur_Latn", "crowdin": "tr"},
+    {"name": "Uyghur", "nllb": "uig_Arab", "crowdin": "ug"},
+    {"name": "Ukrainian", "nllb": "ukr_Cyrl", "crowdin": "uk"},
+    {"name": "Venetian", "nllb": "vec_Latn", "crowdin": "vec"},
+    {"name": "Vietnamese", "nllb": "vie_Latn", "crowdin": "vi"},
+    {"name": "Wolof", "nllb": "wol_Latn", "crowdin": "wo"},
+    {"name": "Xhosa", "nllb": "xho_Latn", "crowdin": "xh"},
+    {"name": "Yoruba", "nllb": "yor_Latn", "crowdin": "yo"},
+    {"name": "Zulu", "nllb": "zul_Latn", "crowdin": "zu"},
+]
+
+NAME_TO_NLLB = {lang["name"]: lang["nllb"] for lang in LANGUAGES}
+NAME_TO_CROWDIN = {lang["name"]: lang["crowdin"] for lang in LANGUAGES}
+CROWDIN_TO_NLLB = {lang["crowdin"]: lang["nllb"] for lang in LANGUAGES}
+NLLB_TO_CROWDIN = {lang["nllb"]: lang["crowdin"] for lang in LANGUAGES}
+CROWDIN_TO_NAME = {lang["crowdin"]: lang["name"] for lang in LANGUAGES}
+NLLB_TO_NAME = {lang["nllb"]: lang["name"] for lang in LANGUAGES}
+
+
+def get_nllb_code(crowdin_code):
+    return CROWDIN_TO_NLLB.get(crowdin_code, crowdin_code)
+
+
+def get_crowdin_code(nllb_code):
+    return NLLB_TO_CROWDIN.get(nllb_code)
+
+
+def get_language_name_by_crowdin(crowdin_code):
+    return CROWDIN_TO_NAME.get(crowdin_code)
+
+
+def get_language_name_by_nllb(nllb_code):
+    return NLLB_TO_NAME.get(nllb_code)
+
+
+def get_language_info(identifier, identifier_type="auto"):
+    if identifier_type == "auto":
+        for lang in LANGUAGES:
+            if (lang["name"].lower() == identifier.lower() or 
+                lang["nllb"] == identifier or 
+                lang["crowdin"] == identifier):
+                return lang
+    elif identifier_type == "name":
+        for lang in LANGUAGES:
+            if lang["name"].lower() == identifier.lower():
+                return lang
+    elif identifier_type == "nllb":
+        for lang in LANGUAGES:
+            if lang["nllb"] == identifier:
+                return lang
+    elif identifier_type == "crowdin":
+        for lang in LANGUAGES:
+            if lang["crowdin"] == identifier:
+                return lang
+    
+    return None
+
+
+def list_all_languages():
+    return [lang["name"] for lang in LANGUAGES]
+
+
+def list_all_nllb_codes():
+    return [lang["nllb"] for lang in LANGUAGES]
+
+
+def list_all_crowdin_codes():
+    return [lang["crowdin"] for lang in LANGUAGES]

whisperlivekit/translation/translation.py

@@ -0,0 +1,37 @@
+import ctranslate2
+import transformers
+from dataclasses import dataclass
+import huggingface_hub
+
+src_lang = "eng_Latn"
+
+@dataclass
+class TranslationModel():
+    translator: ctranslate2.Translator
+    tokenizer: transformers.AutoTokenizer
+
+def load_model(src_lang):
+    huggingface_hub.snapshot_download('entai2965/nllb-200-distilled-600M-ctranslate2',local_dir='nllb-200-distilled-600M-ctranslate2')
+    translator = ctranslate2.Translator("nllb-200-distilled-600M-ctranslate2",device="cpu")
+    tokenizer = transformers.AutoTokenizer.from_pretrained("nllb-200-distilled-600M-ctranslate2", src_lang=src_lang, clean_up_tokenization_spaces=True)
+    return TranslationModel(
+        translator=translator,
+        tokenizer=tokenizer
+        )
+
+def translate(input, translation_model, tgt_lang):
+    if not input:
+        return ""
+    source = translation_model.tokenizer.convert_ids_to_tokens(translation_model.tokenizer.encode(input))
+    target_prefix = [tgt_lang]
+    results = translation_model.translator.translate_batch([source], target_prefix=[target_prefix])
+    target = results[0].hypotheses[0][1:]
+    return translation_model.tokenizer.decode(translation_model.tokenizer.convert_tokens_to_ids(target))
+
+
+if __name__ == '__main__':
+    tgt_lang = "fra_Latn"
+    src_lang = "eng_Latn"
+    translation_model = load_model(src_lang)
+    result = translate('Hello world', translation_model=translation_model, tgt_lang=tgt_lang)
+    print(result)

whisperlivekit/web/src/settings.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M433-80q-27 0-46.5-18T363-142l-9-66q-13-5-24.5-12T307-235l-62 26q-25 11-50 2t-39-32l-47-82q-14-23-8-49t27-43l53-40q-1-7-1-13.5v-27q0-6.5 1-13.5l-53-40q-21-17-27-43t8-49l47-82q14-23 39-32t50 2l62 26q11-8 23-15t24-12l9-66q4-26 23.5-44t46.5-18h94q27 0 46.5 18t23.5 44l9 66q13 5 24.5 12t22.5 15l62-26q25-11 50-2t39 32l47 82q14 23 8 49t-27 43l-53 40q1 7 1 13.5v27q0 6.5-2 13.5l53 40q21 17 27 43t-8 49l-48 82q-14 23-39 32t-50-2l-60-26q-11 8-23 15t-24 12l-9 66q-4 26-23.5 44T527-80h-94Zm7-80h79l14-106q31-8 57.5-23.5T639-327l99 41 39-68-86-65q5-14 7-29.5t2-31.5q0-16-2-31.5t-7-29.5l86-65-39-68-99 42q-22-23-48.5-38.5T533-694l-13-106h-79l-14 106q-31 8-57.5 23.5T321-633l-99-41-39 68 86 64q-5 15-7 30t-2 32q0 16 2 31t7 30l-86 65 39 68 99-42q22 23 48.5 38.5T427-266l13 106Zm42-180q58 0 99-41t41-99q0-58-41-99t-99-41q-59 0-99.5 41T342-480q0 58 40.5 99t99.5 41Zm-2-140Z"/></svg>

whisperlivekit/web/src/translate.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="m603-202-34 97q-4 11-14 18t-22 7q-20 0-32.5-16.5T496-133l152-402q5-11 15-18t22-7h30q12 0 22 7t15 18l152 403q8 19-4 35.5T868-80q-13 0-22.5-7T831-106l-34-96H603ZM362-401 188-228q-11 11-27.5 11.5T132-228q-11-11-11-28t11-28l174-174q-35-35-63.5-80T190-640h84q20 39 40 68t48 58q33-33 68.5-92.5T484-720H80q-17 0-28.5-11.5T40-760q0-17 11.5-28.5T80-800h240v-40q0-17 11.5-28.5T360-880q17 0 28.5 11.5T400-840v40h240q17 0 28.5 11.5T680-760q0 17-11.5 28.5T640-720h-76q-21 72-63 148t-83 116l96 98-30 82-122-125Zm266 129h144l-72-204-72 204Z"/></svg>