Chen Xupeng

Hi, thanks for the fix! I tried the solution on the https://github.com/microsoft/nni/files/9237869/quantization_debug.zip I uploaded above and unfortunately there is another error occurs: KeyError: 18 Maybe this fix could cause some...

Also looking forward to 3D ResNest for medical imaging data!

thanks for the explanation! I could understand that the pitch should not be zero during the silent period. But it is still not making sense to me that the pitch...

by the way I customized some parameters in json file as: ``` { "name": "wavenet_vocoder", "builder": "wavenet", "input_type": "raw", "quantize_channels": 65536, "sample_rate": 16000, "silence_threshold": 2, "num_mels": 32, "fmin": 125, "fmax":...

I think I solved it, I found that although I changed the upsample parameters to [2,4,4,4], the train.py did not receive the parameters, so I change the codes in build_model...

I used the json file you provided in Hyper params URL in Pre-trained models. Do you mean we do not need the upsample_scales parameters anymore? Could you provide the new...

Yeah I checkout to the specific version while trying synthesis. But for training a new model use my own data I think I kind of mixed the older version with...

hey, I'd like to ask again that although the model can be trained smoothly on the specific upsample scale, the model can't be used to synthesize the audio using same...

Hey, I tried to see what happened to upsample_net, I found that when specifying scales to [2, 4, 4, 4] (which supposed to upsample 128). But during training when I...

I did some further debugging and there are still something confusing me: at first in synthesis.py it seems batch_wavegen function's parameter has some problems when applying it in line 243....