diff --git a/configs/config.yaml b/configs/config.yaml index 746e29a..65c7f55 100644 --- a/configs/config.yaml +++ b/configs/config.yaml @@ -1,5 +1,5 @@ # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== -version: 90 +version: 91 binding_name: null model_name: null model_variant: null @@ -186,4 +186,5 @@ activate_audio_infos: true # whisper configuration +whisper_activate: false whisper_model: base \ No newline at end of file diff --git a/lollms/app.py b/lollms/app.py index b5af08a..026e937 100644 --- a/lollms/app.py +++ b/lollms/app.py @@ -266,7 +266,7 @@ class LollmsApplication(LoLLMsCom): self.warning(f"Couldn't load vllm") - if self.config.enable_voice_service: + if self.config.xtts_enable: try: from lollms.services.xtts.lollms_xtts import LollmsXTTS voice=self.config.xtts_current_voice diff --git a/lollms/configs/config.yaml b/lollms/configs/config.yaml index 746e29a..65c7f55 100644 --- a/lollms/configs/config.yaml +++ b/lollms/configs/config.yaml @@ -1,5 +1,5 @@ # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== -version: 90 +version: 91 binding_name: null model_name: null model_variant: null @@ -186,4 +186,5 @@ activate_audio_infos: true # whisper configuration +whisper_activate: false whisper_model: base \ No newline at end of file diff --git a/lollms/server/configs/config.yaml b/lollms/server/configs/config.yaml index 746e29a..65c7f55 100644 --- a/lollms/server/configs/config.yaml +++ b/lollms/server/configs/config.yaml @@ -1,5 +1,5 @@ # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== -version: 90 +version: 91 binding_name: null model_name: null model_variant: null @@ -186,4 +186,5 @@ activate_audio_infos: true # whisper configuration +whisper_activate: false whisper_model: base \ No newline at end of file diff --git a/lollms/server/endpoints/lollms_xtts.py b/lollms/server/endpoints/lollms_xtts.py index ebf8742..5c1e42b 100644 --- a/lollms/server/endpoints/lollms_xtts.py +++ b/lollms/server/endpoints/lollms_xtts.py @@ -123,7 +123,10 @@ async def text2Audio(request: LollmsText2AudioRequest): try: from lollms.services.xtts.lollms_xtts import LollmsXTTS # If the personality has a voice, then use it - if voice!="main_voice": + personality_audio:Path = lollmsElfServer.personality.personality_package_path/"audio" + if personality_audio.exists() and len([v for v in personality_audio.iterdir()])>0: + voices_folder = personality_audio + elif voice!="main_voice": voices_folder = lollmsElfServer.lollms_paths.custom_voices_path else: voices_folder = Path(__file__).parent.parent.parent/"services/xtts/voices"