feat: support get model languages

gpustack · Nov 28, 2024 · ec57b83 · ec57b83
1 parent 9337460
commit ec57b83
Show file tree

Hide file tree

Showing 3 changed files with 127 additions and 0 deletions.
diff --git a/vox_box/backends/stt/faster_whisper.py b/vox_box/backends/stt/faster_whisper.py
@@ -61,10 +61,13 @@ def load(self):
             compute_type=compute_type,
         )
 
+        self._languages = self._get_languages()
+
         self._model_dict = create_model_dict(
             self._cfg.model,
             task_type=TaskTypeEnum.STT,
             backend_framework=BackendEnum.FASTER_WHISPER,
+            languages=self._languages,
         )
         self.model_load = True
         return self
@@ -146,3 +149,108 @@ def transcribe(
                 response["segments"] = timestamps
 
             return response
+
+    def _get_languages(self) -> List[Dict]:
+        return [
+            {"auto": "auto"},
+            {"en": "english"},
+            {"zh": "chinese"},
+            {"de": "german"},
+            {"es": "spanish"},
+            {"ru": "russian"},
+            {"ko": "korean"},
+            {"fr": "french"},
+            {"ja": "japanese"},
+            {"pt": "portuguese"},
+            {"pl": "polish"},
+            {"ca": "catalan"},
+            {"nl": "dutch"},
+            {"it": "italian"},
+            {"th": "thai"},
+            {"tr": "turkish"},
+            {"ar": "arabic"},
+            {"sv": "swedish"},
+            {"id": "indonesian"},
+            {"hi": "hindi"},
+            {"fi": "finnish"},
+            {"vi": "vietnamese"},
+            {"he": "hebrew"},
+            {"uk": "ukrainian"},
+            {"el": "greek"},
+            {"ms": "malay"},
+            {"cs": "czech"},
+            {"ro": "romanian"},
+            {"da": "danish"},
+            {"hu": "hungarian"},
+            {"ta": "tamil"},
+            {"no": "norwegian"},
+            {"ur": "urdu"},
+            {"hr": "croatian"},
+            {"bg": "bulgarian"},
+            {"lt": "lithuanian"},
+            {"la": "latin"},
+            {"mi": "maori"},
+            {"ml": "malayalam"},
+            {"cy": "welsh"},
+            {"sk": "slovak"},
+            {"te": "telugu"},
+            {"fa": "persian"},
+            {"lv": "latvian"},
+            {"bn": "bengali"},
+            {"sr": "serbian"},
+            {"az": "azerbaijani"},
+            {"sl": "slovenian"},
+            {"kn": "kannada"},
+            {"et": "estonian"},
+            {"mk": "macedonian"},
+            {"br": "breton"},
+            {"eu": "basque"},
+            {"is": "icelandic"},
+            {"hy": "armenian"},
+            {"ne": "nepali"},
+            {"mn": "mongolian"},
+            {"bs": "bosnian"},
+            {"kk": "kazakh"},
+            {"sq": "albanian"},
+            {"sw": "swahili"},
+            {"gl": "galician"},
+            {"mr": "marathi"},
+            {"pa": "punjabi"},
+            {"si": "sinhala"},
+            {"km": "khmer"},
+            {"sn": "shona"},
+            {"yo": "yoruba"},
+            {"so": "somali"},
+            {"af": "afrikaans"},
+            {"oc": "occitan"},
+            {"ka": "georgian"},
+            {"be": "belarusian"},
+            {"tg": "tajik"},
+            {"sd": "sindhi"},
+            {"gu": "gujarati"},
+            {"am": "amharic"},
+            {"yi": "yiddish"},
+            {"lo": "lao"},
+            {"uz": "uzbek"},
+            {"fo": "faroese"},
+            {"ht": "haitian creole"},
+            {"ps": "pashto"},
+            {"tk": "turkmen"},
+            {"nn": "nynorsk"},
+            {"mt": "maltese"},
+            {"sa": "sanskrit"},
+            {"lb": "luxembourgish"},
+            {"my": "myanmar"},
+            {"bo": "tibetan"},
+            {"tl": "tagalog"},
+            {"mg": "malagasy"},
+            {"as": "assamese"},
+            {"tt": "tatar"},
+            {"haw": "hawaiian"},
+            {"ln": "lingala"},
+            {"ha": "hausa"},
+            {"ba": "bashkir"},
+            {"jw": "javanese"},
+            {"su": "sundanese"},
+            {"yue": "cantonese"},
+        ]
diff --git a/vox_box/backends/stt/funasr.py b/vox_box/backends/stt/funasr.py
@@ -50,10 +50,14 @@ def load(self):
             log_level=self._log_level,
             disable_update=True,
         )
+
+        self._languages = self._get_languages()
+
         self._model_dict = create_model_dict(
             self._cfg.model,
             task_type=TaskTypeEnum.STT,
             backend_framework=BackendEnum.FUN_ASR,
+            languages=self._languages,
         )
         self._model_load = True
         return self
@@ -106,3 +110,8 @@ def transcribe(
 
             text = rich_transcription_postprocess(res[0]["text"])
             return text
+
+    def _get_languages(self) -> List[Dict]:
+        return [
+            {"auto": "auto"},
+        ]
diff --git a/vox_box/server/routers.py b/vox_box/server/routers.py
@@ -188,6 +188,16 @@ async def get_model_info(model_id: str):
     return model_instance.model_info()
 
 
+@router.get("/v1/languages")
+async def get_languages():
+    model_instance = get_model_instance()
+    if model_instance is None:
+        return {}
+    return {
+        "languages": model_instance.model_info().get("languages", []),
+    }
+
+
 @router.get("/v1/voices")
 async def get_voice():
     model_instance = get_model_instance()