Maas-Agent/apps/models_provider/impl/tencent_model_provider/model/stt.py

# coding=utf-8
import io
from typing import Dict

from models_provider.base_model_provider import MaxKBBaseModel
from models_provider.impl.base_stt import BaseSpeechToText


class TencentSpeechToText(MaxKBBaseModel, BaseSpeechToText):
    secret_id: str
    secret_key: str
    model: str

    @staticmethod
    def is_cache_model():
        return False

    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.secret_id = kwargs.get('secret_id')
        self.secret_key = kwargs.get('secret_key')
        self.model = kwargs.get('model')

    @staticmethod
    def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
        return TencentSpeechToText(
            model=model_name,
            secret_id=model_credential.get('secret_id'),
            secret_key=model_credential.get('secret_key'),
            **model_kwargs,
        )

    def check_auth(self):
        pass

    def speech_to_text(self, audio_file):
        return "Tencent STT not implemented"