refactor: Support different types of aliyun stt model

zhanweizhang7 · zhanweizhang7 · commit 6c1451f0e187 · 2025-12-05T17:38:24.000+08:00
diff --git a/apps/locales/en_US/LC_MESSAGES/django.po b/apps/locales/en_US/LC_MESSAGES/django.po
@@ -8805,4 +8805,13 @@ msgid "File upload is not enabled"
 msgstr ""
 
 msgid "Blocked unsafe redirect to internal host"
+msgstr ""
+
+msgid "Audio file recognition - Tongyi Qwen"
+msgstr ""
+
+msgid "Audio file recognition - Fun-ASR/Paraformer/SenseVoice"
+msgstr ""
+
+msgid "Qwen-Omni"
 msgstr ""
diff --git a/apps/locales/zh_CN/LC_MESSAGES/django.po b/apps/locales/zh_CN/LC_MESSAGES/django.po
@@ -8931,4 +8931,14 @@ msgid "File upload is not enabled"
 msgstr "文件上传未启用"
 
 msgid "Blocked unsafe redirect to internal host"
-msgstr "阻止不安全的重定向到内部主机"
+msgstr "阻止不安全的重定向到内部主机"
+msgstr "请输入Web根地址"
+
+msgid "Audio file recognition - Tongyi Qwen"
+msgstr "录音文件识别-通义千问"
+
+msgid "Audio file recognition - Fun-ASR/Paraformer/SenseVoice"
+msgstr "录音文件识别-Fun-ASR/Paraformer/SenseVoice"
+
+msgid "Qwen-Omni"
+msgstr "多模态"
diff --git a/apps/locales/zh_Hant/LC_MESSAGES/django.po b/apps/locales/zh_Hant/LC_MESSAGES/django.po
@@ -8932,3 +8932,14 @@ msgstr "文件上傳未啟用"
 
 msgid "Blocked unsafe redirect to internal host"
 msgstr "阻止不安全的重定向到內部主機"
+
+msgstr "請輸入Web根地址"
+
+msgid "Audio file recognition - Tongyi Qwen"
+msgstr "錄音文件識別-通義千問"
+
+msgid "Audio file recognition - Fun-ASR/Paraformer/SenseVoice"
+msgstr "錄音文件識別-Fun-ASR/Paraformer/SenseVoice"
+
+msgid "Qwen-Omni"
+msgstr "多模態"
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/aliyun_bai_lian_model_provider.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/aliyun_bai_lian_model_provider.py
@@ -11,26 +11,28 @@
 from common.utils.common import get_file_content
 from models_provider.base_model_provider import ModelProvideInfo, ModelTypeConst, ModelInfo, IModelProvider, \
     ModelInfoManage
-from models_provider.impl.aliyun_bai_lian_model_provider.credential.asr_stt import AliyunBaiLianAsrSTTModelCredential
+from models_provider.impl.aliyun_bai_lian_model_provider.credential.stt.asr_stt import AliyunBaiLianAsrSTTModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.embedding import \
     AliyunBaiLianEmbeddingCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.image import QwenVLModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.itv import ImageToVideoModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.llm import BaiLianLLMModelCredential
-from models_provider.impl.aliyun_bai_lian_model_provider.credential.omni_stt import AliyunBaiLianOmiSTTModelCredential
+from models_provider.impl.aliyun_bai_lian_model_provider.credential.stt.omni_stt import AliyunBaiLianOmiSTTModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.reranker import \
     AliyunBaiLianRerankerCredential
-from models_provider.impl.aliyun_bai_lian_model_provider.credential.stt import AliyunBaiLianSTTModelCredential
+from models_provider.impl.aliyun_bai_lian_model_provider.credential.stt import AliyunBaiLianSTTModelCredential, \
+    AliyunBaiLianDefaultSTTModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.tti import QwenTextToImageModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.tts import AliyunBaiLianTTSModelCredential
 from models_provider.impl.aliyun_bai_lian_model_provider.credential.ttv import TextToVideoModelCredential
-from models_provider.impl.aliyun_bai_lian_model_provider.model.asr_stt import AliyunBaiLianAsrSpeechToText
+from models_provider.impl.aliyun_bai_lian_model_provider.model.stt.asr_stt import AliyunBaiLianAsrSpeechToText
 from models_provider.impl.aliyun_bai_lian_model_provider.model.embedding import AliyunBaiLianEmbedding
 from models_provider.impl.aliyun_bai_lian_model_provider.model.image import QwenVLChatModel
 from models_provider.impl.aliyun_bai_lian_model_provider.model.llm import BaiLianChatModel
-from models_provider.impl.aliyun_bai_lian_model_provider.model.omni_stt import AliyunBaiLianOmiSpeechToText
+from models_provider.impl.aliyun_bai_lian_model_provider.model.stt.omni_stt import AliyunBaiLianOmiSpeechToText
 from models_provider.impl.aliyun_bai_lian_model_provider.model.reranker import AliyunBaiLianReranker
-from models_provider.impl.aliyun_bai_lian_model_provider.model.stt import AliyunBaiLianSpeechToText
+from models_provider.impl.aliyun_bai_lian_model_provider.model.stt import AliyunBaiLianSpeechToText, \
+    AliyunBaiLianDefaultSpeechToText
 from models_provider.impl.aliyun_bai_lian_model_provider.model.tti import QwenTextToImageModel
 from models_provider.impl.aliyun_bai_lian_model_provider.model.tts import AliyunBaiLianTextToSpeech
 from maxkb.conf import PROJECT_DIR
@@ -43,6 +45,7 @@
 aliyun_bai_lian_stt_model_credential = AliyunBaiLianSTTModelCredential()
 aliyun_bai_lian_omi_stt_model_credential = AliyunBaiLianOmiSTTModelCredential()
 aliyun_bai_lian_asr_stt_model_credential = AliyunBaiLianAsrSTTModelCredential()
+aliyun_bai_lian_default_stt_model_credential = AliyunBaiLianDefaultSTTModelCredential()
 aliyun_bai_lian_embedding_model_credential = AliyunBaiLianEmbeddingCredential()
 aliyun_bai_lian_llm_model_credential = BaiLianLLMModelCredential()
 qwenvl_model_credential = QwenVLModelCredential()
@@ -137,7 +140,10 @@
     .append_model_info_list(module_info_tti_list)
     .append_default_model_info(module_info_tti_list[0])
     .append_default_model_info(model_info_list[1])
-    .append_default_model_info(model_info_list[2])
+    .append_default_model_info(ModelInfo('default',
+                             _('default'),
+                             ModelTypeConst.STT, aliyun_bai_lian_default_stt_model_credential,
+                             AliyunBaiLianDefaultSpeechToText))
     .append_default_model_info(model_info_list[3])
     .append_default_model_info(model_info_list[4])
     .append_default_model_info(model_info_list[0])
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/__init__.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/__init__.py
@@ -0,0 +1,12 @@
+# coding=utf-8
+"""
+    @project: MaxKB
+    @Author：niu
+    @file： __init__.py.py
+    @date：2025/12/5 15:11
+    @desc:
+"""
+from .stt import AliyunBaiLianSTTModelCredential
+from .omni_stt import AliyunBaiLianOmiSTTModelCredential
+from .default_stt import AliyunBaiLianDefaultSTTModelCredential
+from .asr_stt import AliyunBaiLianAsrSTTModelCredential
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/asr_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/asr_stt.py
@@ -8,6 +8,7 @@
 from django.utils.translation import gettext as _
 from common.utils.logger import maxkb_logger
 
+
 class AliyunBaiLianAsrSTTModelCredential(BaseForm, BaseModelCredential):
     api_url = forms.TextInputField(_('API URL'), required=True)
     api_key = forms.PasswordInputField(_('API Key'), required=True)
@@ -39,6 +40,7 @@ def is_valid(self,
 
         try:
             model = provider.get_model(model_type, model_name, model_credential)
+            model.check_auth()
         except Exception as e:
             maxkb_logger.error(f'Exception: {e}', exc_info=True)
             if isinstance(e, AppApiException):
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/default_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/default_stt.py
@@ -0,0 +1,84 @@
+# coding=utf-8
+"""
+    @project: MaxKB
+    @Author：niu
+    @file： default_stt.py
+    @date：2025/12/5 15:12
+    @desc:
+"""
+from typing import Dict, Any
+
+from common import forms
+from common.exception.app_exception import AppApiException
+from common.forms import BaseForm
+from maxkb.settings import maxkb_logger
+from models_provider.base_model_provider import BaseModelCredential, ValidCode
+from django.utils.translation import gettext as _
+
+
+
+class AliyunBaiLianDefaultSTTModelCredential(BaseForm, BaseModelCredential):
+    type = forms.Radio(_("Type"), required=True, text_field='label', default_value='qwen', provider='', method='',
+                       value_field='value', option_list=[
+            {'label': _('Audio file recognition - Tongyi Qwen'),
+             'value': 'qwen'},
+            {'label': _('Qwen-Omni'),
+             'value': 'omni'},
+            {'label': _('Audio file recognition - Fun-ASR/Paraformer/SenseVoice'),
+             'value': 'other'}
+        ])
+    api_url = forms.TextInputField(_('API URL'), required=True, relation_show_field_dict={'type': ['qwen', 'omni']})
+    api_key = forms.PasswordInputField(_('API Key'), required=True)
+
+    def is_valid(self,
+                 model_type: str,
+                 model_name: str,
+                 model_credential: Dict[str, Any],
+                 model_params: Dict[str, Any],
+                 provider,
+                 raise_exception: bool = False
+                 ) -> bool:
+        model_type_list = provider.get_model_type_list()
+        model_type_list = provider.get_model_type_list()
+        if not any(mt.get('value') == model_type for mt in model_type_list):
+            raise AppApiException(
+                ValidCode.valid_error.value,
+                _('{model_type} Model type is not supported').format(model_type=model_type)
+            )
+
+        required_keys = ['api_key']
+        for key in required_keys:
+            if key not in model_credential:
+                if raise_exception:
+                    raise AppApiException(
+                        ValidCode.valid_error.value,
+                        _('{key} is required').format(key=key)
+                    )
+                return False
+
+        try:
+            model = provider.get_model(model_type, model_name, model_credential)
+            model.check_auth()
+        except Exception as e:
+            maxkb_logger.error(f'Exception: {e}', exc_info=True)
+            if isinstance(e, AppApiException):
+                raise e
+            if raise_exception:
+                raise AppApiException(
+                    ValidCode.valid_error.value,
+                    _('Verification failed, please check whether the parameters are correct: {error}').format(
+                        error=str(e))
+                )
+            return False
+        return True
+
+    def encryption_dict(self, model: Dict[str, object]) -> Dict[str, object]:
+
+        return {
+            **model,
+            'api_key': super().encryption(model.get('api_key', ''))
+        }
+
+    def get_model_params_setting_form(self, model_name):
+
+        pass
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/omni_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/omni_stt.py
@@ -48,6 +48,7 @@ def is_valid(self,
 
         try:
             model = provider.get_model(model_type, model_name, model_credential)
+            model.check_auth()
         except Exception as e:
             maxkb_logger.error(f'Exception: {e}', exc_info=True)
             if isinstance(e, AppApiException):
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/stt/stt.py
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/__init__.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/__init__.py
@@ -0,0 +1,13 @@
+#coding=utf-8
+"""
+    @project: MaxKB
+    @Author：niu
+    @file： __init__.py.py
+    @date：2025/12/5 15:39
+    @desc:
+"""
+
+from .asr_stt import AliyunBaiLianAsrSpeechToText
+from .default_stt import AliyunBaiLianDefaultSpeechToText
+from .stt import AliyunBaiLianSpeechToText
+from .omni_stt import AliyunBaiLianOmiSpeechToText
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/asr_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/asr_stt.py
@@ -43,6 +43,7 @@ def check_auth(self):
             self.speech_to_text(audio_file)
 
     def speech_to_text(self, audio_file):
+
         try:
 
             base64_audio = base64.b64encode(audio_file.read()).decode("utf-8")
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/default_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/default_stt.py
@@ -0,0 +1,68 @@
+# coding=utf-8
+"""
+    @project: MaxKB
+    @Author：niu
+    @file： default_stt.py
+    @date：2025/12/5 15:40
+    @desc:
+"""
+import os
+from typing import Dict
+
+from models_provider.base_model_provider import MaxKBBaseModel
+
+from models_provider.impl.base_stt import BaseSpeechToText
+
+
+class AliyunBaiLianDefaultSpeechToText(MaxKBBaseModel, BaseSpeechToText):
+    def check_auth(self):
+        pass
+
+    def speech_to_text(self, audio_file):
+        pass
+
+    @staticmethod
+    def is_cache_model():
+        return False
+
+    @staticmethod
+    def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
+        from models_provider.impl.aliyun_bai_lian_model_provider.model.stt import AliyunBaiLianOmiSpeechToText, \
+            AliyunBaiLianSpeechToText, AliyunBaiLianAsrSpeechToText
+        stt_type=model_credential.get('type')
+        if stt_type == 'qwen':
+            return AliyunBaiLianAsrSpeechToText(
+                model=model_name,
+                api_key=model_credential.get('api_key'),
+                api_url=model_credential.get('api_url'),
+                params=model_kwargs,
+                **model_kwargs
+            )
+        elif stt_type == 'omni':
+            return AliyunBaiLianOmiSpeechToText(
+                model=model_name,
+                api_key=model_credential.get('api_key'),
+                api_url=model_credential.get('api_url'),
+                params=model_kwargs,
+                **model_kwargs
+            )
+        else:
+            return AliyunBaiLianSpeechToText(
+                model=model_name,
+                api_key=model_credential.get('api_key'),
+                params=model_kwargs,
+                **model_kwargs,
+            )
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/iat_mp3_16k.mp3 b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/iat_mp3_16k.mp3
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/omni_stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/omni_stt.py
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/stt.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/stt/stt.py
