geneing

Results 21 comments of geneing

1. Make sure that input mel is correct - e.g. use one of the training set inputs. 2. It may be easier to debug using python library sys.path.insert(0,'lib/build-src-RelDebInfo') #use correct...

@maozhiqiang Could you, please, attach the mel data you are using as an input. Then I can try to reproduce your problem.

@maozhiqiang Works for me with b2f5fc106. ![Screenshot_20190321_232140](https://user-images.githubusercontent.com/10255558/54804454-c6440b00-4c30-11e9-85eb-e921e2527742.png) [test.zip](https://github.com/geneing/WaveRNN-Pytorch/files/2995237/test.zip) Commands: import numpy as np import librosa import sys sys.path.insert(0,'../WaveRNN-Pytorch/lib/build-src-RelDebInfo') import WaveRNNVocoder mel=np.load('eval/test_0_mel.npy') vocoder=WaveRNNVocoder.Vocoder() vocoder.loadWeights('../WaveRNN-Pytorch/model_outputs/model.bin') wav=vocoder.melToWav(mel) plot(wav) librosa.output.write_wav('test.wav', wav, 16000) The speech...

I'm not sure how to help you. Here's the weight file I'm using. [model.bin.zip](https://github.com/geneing/WaveRNN-Pytorch/files/2999043/model.bin.zip)

@alexdemartos Would it be possible for you to obtain the stack trace when this error happens. You may have to recompile in debug mode and either run with gdb or...

@acrosson The network in this repo is designed for best performance on CPU - low op count, branching and memory access optimized for pipelined processors. For best performance on GPU...

@bshall Well, the main reason for simplified upsampling was to improve data flow. The upsampling part contains a 5 tap convolution, which requires padding the input mels on both sides...

@rishikksh20 Could you please set a breakpoint in dataset.py line 132 and check what max_offsets list contains. If it contains negative offsets, then could you please check "batch" list and...

@rishikksh20 I've been using two datasets LJSpeech and M-AILABS (Mary Ann reader). Both are ~24 hours of speech. I haven't tried smaller datasets because I use the same dataset for...

Looks like magzdb switched to https from http. Here's what's going on: 1. In _html_regex the requests.get command uses allow_redirect=False 2. Without redirect docstring gets "301 Moved Permanently" response. The...