Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.
Thanks for your amazing project sherpa-ncnn and it provide an alternative excellent ASR engine to open source community and developers.
Could you implement TTS using next-generation Kaldi with ncnn inference framework in this project(just like what you did in sherpa-onnx )? it will helpful for developers because ncnn inference framework is well-maintained and ncnn inference frameworks is widely deployed in QQ/WeChat and some developers don't want to use ONNX inference framework on Android device.
It will great helpful for developers if you provide ASR&TTS using next-generation Kaldi with ncnn in this standalone project and developers can use a single inference framework to do ASR/TTS task with the powerful Kaldi in Android application at the same time.
Thanks for your amazing project sherpa-ncnn and it provide an alternative excellent ASR engine to open source community and developers.
Could you implement TTS using next-generation Kaldi with ncnn inference framework in this project(just like what you did in sherpa-onnx )? it will helpful for developers because ncnn inference framework is well-maintained and ncnn inference frameworks is widely deployed in QQ/WeChat and some developers don't want to use ONNX inference framework on Android device.
It will great helpful for developers if you provide ASR&TTS using next-generation Kaldi with ncnn in this standalone project and developers can use a single inference framework to do ASR/TTS task with the powerful Kaldi in Android application at the same time.