I am an avid learner who is trying to figure if this is something to drill my attention into. I have found a TTS engine which is *" developed on the basis of TensorflowTTS, used for TfLite model testing.
this is the github: GitHub - benjaminwan/ChineseTtsTflite: Android Chinese TTS Engine Base On Tensorflow TTS , use for TfLite Models Test。安卓离线中文TTS引擎,在TensorflowTTS基础上开发,用于TfLite模型测试。
I think it is really nifty and I’m trying to learn the nomenclature to understand how one would test a Tflite model. I specifically looking into seeing if I can switch this into a english speaking TTS engine.
The author has said that there is some English models which already exist and I have attempted to use these and alter his application with these models. I think I have done something incorrect but im not knowledgeable enough to know what yet.
What I have done:
- Attempted to swap in the english model in place of the chinese model files. (file ext: .tflite)
I got the english model from another demo which does a similar function to the chinese app, though it does not have an engine function (source: TensorFlowTTS/examples/android at master · TensorSpeech/TensorFlowTTS · GitHub)
- Tried reading the guide (https://www.tensorflow.org/lite/android/quickstart) to see if it will help me understand how to reverse engineer the application, though it seems I have been having trouble.
I hope that I have provided some understandable information for what I am trying to do. Let me know if you have any suggestions or ideas of how I could approach this.