no example code ?
were is the example python implementation to call this model or use it in a project ? can it be converted and used as a gguf ? how ? or is this only for C# user and onnx formats or just raw usage ? what is the outputs ?
Please refer to the Installation and Usage Sections. You can build your own real-time websocket demo or inference from text file directly.
i understand this non standard way of using tts model !
the question become why are you not using standardiazed methodologys and creating these extra overhead models and services ?
this is the current issues with microsoft outputs right now :
Every thing is OUTSIDE ! the community !
its OUTSIDE ~ the standard execution pipelines !
excuses given and redirection to BAD documentation ? BAD examples or usage ?
WHY ?
its a very small model built off the qwen ? why not release a quantized model or fit it into the standard TTS pytoipelines that are already existing ?||
it make the model only valuable as a cameo demo !
ie eleven labs is a paid ! but its used not for the price ! its used for the standard pipeline as it fits many devlopers modality !
now how many servers should we run just to load a single model and produce a speech output ? should it be complicated ? ...
so in truth i think this does nt seem like a expected microsoft output ! as it is very low quality in usablity and documaetation ?
aha like semantic kernal and AI builder etc ? now converted into AI-framwork also maybe outside the AI community ! so also will be dropped by most !
ITs impoetant to fit the current Schema and devolopment models or it becomes unused and non valuable !
Edge tts / Orpheous / CSM ? these are examples ( not the best but they are creating a standard ! ) ..em i dont think they use servers and waste resources either as they are one shot !
as well as fit easily into existing environment without taking up resources
hence i ask for the implementation and you sent me to another forum to disect ! making it worthless and uncomfortable just to test !! or even deploy !