西西 comments

Results 9 comments of


                                            西西

Conv2DCustomBackpropInputOp only supports NHWC.

can't work on ubuntu16.04 and tf1.15

[BUG] Different inference results of tflite model and onnx model(convert from tflite model)

I also encountered this problem, did you solve it?

Make train: raise ValueError('value should be one of int, float, str, bool, or torch.Tensor')

Have you solved this problem?

Use mel-gan as an universal vocoder

In my experiment， just shift to your own data and continue training when base model (for example, training from LJSpeech) training is done, you will get a result good as...

Synthesis time is high on a Jetson TX2 GPU

your frozen model is ckpt or pb on tx2?

what is the inference time in GPU?.

> how long LPCtron takes to synthesize 2 secs of audio in CPU? have you done this experiments?

child方法

Any solution?

ADD A NEW LANGUAGE

run lora inference will report error when i modify the lora rank to 64.

ADD A NEW LANGUAGE

> run lora inference will report error when i modify the lora rank to 64. lora_ft_webui_infer.py#Line269, "lora_selection" should be pass to the load_model function