GeorgeS2019

All effort with e.g. 4.0, 4.1, 4.3 [failed](https://github.com/microsoft/vcpkg/issues/44695#issuecomment-2982232314) @BillyONeal

Promote directly at the Torchsharp discussion...tell people what U have learned and what are needed next

There are 3 Microsoft engineers dedicated to keep it going...strategic to ML.net and agent Ai for Dotnet. Please keep pushing and ask for feedback...perhaps the 3 engineers can coordinate with...

Currently, it is unclear if the existing implementation of TorchVision requires the [c++ part of the PyTorch Vision. ](https://github.com/pytorch/vision/tree/main/torchvision/csrc)**Anyone know this answer?** #Suggestion > perhaps this is the c++ file...

Hi @ozanMSFT ### part1 > If you're looking for the examples, I suggest you to visit: https://github.com/dotnet/TorchSharpExamples @whuanle is not looking for example...in contrary..he is addressing important missing part of...

@ozanMSFT Perhaps start introducing label: TorchVision, TorchAudio

@csukuangfj It is challenging to know for each of the above case, which models to use for **German** and the links needed to download the models Priorities are **Real time...

German TTS model from piper ### thorsten-medium - https://huggingface.co/csukuangfj/vits-piper-de_DE-thorsten-medium/tree/main --- - csukuangfj/vits-piper-de_DE-thorsten-high - csukuangfj/vits-piper-de_DE-thorsten-medium - csukuangfj/vits-piper-de_DE-thorsten_emotional-medium - csukuangfj/vits-piper-de_DE-ramona-low - csukuangfj/vits-piper-de_DE-thorsten-low - csukuangfj/vits-piper-de_DE-pavoque-low - csukuangfj/vits-piper-de_DE-kerstin-low - csukuangfj/vits-piper-de_DE-karlsson-low - csukuangfj/vits-piper-de_DE-eva_k-x_low

Differences between ### TTS dotnet examples - https://github.com/k2-fsa/sherpa-onnx/blob/master/dotnet-examples/offline-tts-play - https://github.com/k2-fsa/sherpa-onnx/tree/master/dotnet-examples/offline-tts

https://github.com/k2-fsa/sherpa-onnx/tree/master/dotnet-examples/speech-recognition-from-microphone ## **ASR-Transducer** and **ASR-Paraformer** The **ASR-Transducer** and **ASR-Paraformer** are both models used in automatic speech recognition (ASR) within the Sherpa-ONNX framework, but they have some key differences: ### ASR-Transducer...