changed names

configs/config.yaml

@@ -1,5 +1,5 @@
 # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== 
-version: 98
+version: 99
 binding_name: null
 model_name: null
 model_variant: null
@@ -85,7 +85,7 @@ copy_to_clipboard_add_all_details: false
 active_tts_service: "None" # xtts (offline), openai_tts (API key required)
 active_tti_service: "None" # autosd (offline), dall-e (online)
 active_stt_service: "None" # whisper (offline), asr (offline or online), openai_whiosper (API key required)
-
+active_ttm_service: "None" # musicgen (offline)
 # -------------------- Services --------------------------
 
 # ***************** STT *****************

lollms/app.py

@@ -320,7 +320,7 @@ class LollmsApplication(LoLLMsCom):
             self.tts = self.xtts
 
         if self.config.active_stt_service == "openai_whisper":
-            from lollms.services.openai_whisper.lollms_whisper import LollmsOpenAIWhisper
+            from lollms.services.openai_whisper.lollms_openai_whisper import LollmsOpenAIWhisper
             self.stt = LollmsOpenAIWhisper(self, self.config.openai_whisper_model, self.config.openai_whisper_key)
         elif self.config.active_stt_service == "whisper":
             from lollms.services.whisper.lollms_whisper import LollmsWhisper
@@ -413,7 +413,7 @@ class LollmsApplication(LoLLMsCom):
                 self.tts = self.xtts
 
             if self.config.active_stt_service == "openai_whisper":
-                from lollms.services.openai_whisper.lollms_whisper import LollmsOpenAIWhisper
+                from lollms.services.openai_whisper.lollms_openai_whisper import LollmsOpenAIWhisper
                 self.stt = LollmsOpenAIWhisper(self, self.config.openai_whisper_model, self.config.openai_whisper_key)
             elif self.config.active_stt_service == "whisper":
                 from lollms.services.whisper.lollms_whisper import LollmsWhisper

lollms/configs/config.yaml

@@ -1,5 +1,5 @@
 # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== 
-version: 98
+version: 99
 binding_name: null
 model_name: null
 model_variant: null
@@ -85,7 +85,7 @@ copy_to_clipboard_add_all_details: false
 active_tts_service: "None" # xtts (offline), openai_tts (API key required)
 active_tti_service: "None" # autosd (offline), dall-e (online)
 active_stt_service: "None" # whisper (offline), asr (offline or online), openai_whiosper (API key required)
-
+active_ttm_service: "None" # musicgen (offline)
 # -------------------- Services --------------------------
 
 # ***************** STT *****************

lollms/server/endpoints/lollms_tts.py

@@ -42,6 +42,18 @@ def list_voices():
     ASCIIColors.yellow("Listing voices")
     return {"voices":lollmsElfServer.tts.get_voices()}
 
+@router.get("/list_stt_models")
+def list_stt_models():
+    if lollmsElfServer.config.headless_server_mode:
+        return {"status":False,"error":"Code execution is blocked when in headless mode for obvious security reasons!"}
+
+    if lollmsElfServer.config.host!="localhost" and lollmsElfServer.config.host!="127.0.0.1":
+        return {"status":False,"error":"Code execution is blocked when the server is exposed outside for very obvious reasons!"}
+
+    ASCIIColors.yellow("Listing voices")
+    return {"voices":lollmsElfServer.stt.get_models()}
+
+
 @router.post("/set_voice")
 async def set_voice(request: Request):
     """
@@ -70,7 +82,7 @@ async def set_voice(request: Request):
 
 class LollmsAudio2TextRequest(BaseModel):
     wave_file_path: str
-    voice: str = None
+    model: str = None
     fn:str = None
 
 @router.post("/audio2text")

lollms/services/openai_whisper/lollms_openai_whisper.py

@@ -26,6 +26,7 @@ from typing import List, Dict, Any
 from ascii_colors import ASCIIColors, trace_exception
 from lollms.paths import LollmsPaths
 from lollms.utilities import PackageManager, find_next_available_filename
+from lollms.stt import LollmsSTT
 import subprocess
 import shutil
 from tqdm import tqdm
@@ -34,10 +35,7 @@ from io import BytesIO
 from openai import OpenAI
 
 
-def get_Whisper(lollms_paths:LollmsPaths):
-    return LollmsOpenAIWhisper
-
-class LollmsOpenAIWhisper:
+class LollmsOpenAIWhisper(LollmsSTT):
     def __init__(
                     self, 
                     app:LollmsApplication, 
@@ -45,10 +43,8 @@ class LollmsOpenAIWhisper:
                     api_key="",
                     output_path=None
                     ):
+        super().__init__(app, model, output_path)
         self.client = OpenAI(api_key=api_key)
-        self.app = app
-        self.model = model
-        self.output_path = output_path
         self.ready = True
 
     def transcribe(
@@ -67,4 +63,4 @@ class LollmsOpenAIWhisper:
             file=audio_file,
             response_format="text"
         )        
-        return transcription
+        return transcription

lollms/services/whisper/lollms_whisper.py

@@ -30,13 +30,13 @@ class LollmsWhisper(LollmsSTT):
                     model="small",
                     output_path=None
                     ):
-        self.app = app
-        self.output_path = output_path
+        super().__init__(app, model, output_path)
         self.whisper = whisper.load_model(model)
+        self.ready = True
 
     def transcribe(
                 self,
-                wav_path: str|Path
+                wave_path: str|Path
                 ):
-        result = self.whisper.transcribe(str(wav_path))
+        result = self.whisper.transcribe(str(wave_path))
         return result

lollms/stt.py

@@ -24,7 +24,8 @@ class LollmsSTT:
                     self, 
                     app: LollmsApplication, 
                     model="",
-                    output_path=None
+                    output_path=None,
+                    models=[]
                     ):
         """
         Initializes the LollmsSTT class with the given parameters.
@@ -38,6 +39,7 @@ class LollmsSTT:
         self.app = app
         self.output_path = output_path
         self.model = model
+        self.models = models
 
     def transcribe(
                 self,
@@ -52,7 +54,10 @@ class LollmsSTT:
             prompt (str, optional): An optional prompt to guide the transcription. Defaults to an empty string.
         """
         pass
-
+    
+    def get_models(self):
+        return self.models
+    
     @staticmethod
     def verify(app: LollmsApplication) -> bool:
         """
@@ -90,4 +95,4 @@ class LollmsSTT:
         Returns:
             LollmsSTT: The LollmsSTT class.
         """
-        return LollmsSTT
+        return LollmsSTT