Open zhuyu14 opened 1 year ago
error: illegal scale: INF That probably mean there is INF value in one tensor in the model.
hi @thaink , is there any way to know which tensor gets the illegal value when quantize the model ?
It seems not straight forward now, the model is converted to tflite before quantization so we might have to add log somewhere in the calibration part.
I wonder, there seems to be TensorflowTTS model for TFLite (https://github.com/TensorSpeech/TensorFlowTTS/tree/master/examples/cpptflite). Isn't that suitable for your case?
hi @thaink , yes the model is from the site you showed and the model there is float tflite model ,but in my case , I need int8 tflite model to accelerate inference speed .
I see. @sngyhan TTS model will require dynamic-range quantization, right? Can you guide @zhuyu14 how to do that?
Hi Everyone,
I tried to post quantize fastspeech2 model of TensorFlowTTS ,but got the error message, I was wondering if anyone knows the detials of this error and how to fix this ? Thanks!
Use python version : 3.8.10 Use tensorflow version : 2.8.0
test code:
error log:
Models information and weights are from here: https://huggingface.co/tensorspeech/tts-fastspeech2-ljspeech-en/tree/main https://github.com/TensorSpeech/TensorFlowTTS