byuns9334

Hi, I am trying to execute predict.lua on some toy text and wav file of Librispeech. the toy text (test.txt) is : HE HOPED THERE WOULD BE STEW FOR DINNER...

I get the same training error by every epoch

2

I'm running " th Train.lua -epochSave -learningRateAnnealing 1.1 -trainingSetLMDBPath prepare_datasets/libri_lmdb/train/ -validationSetLMDBPath prepare_datasets/libri_lmdb/test/ -LSTM -hiddenSize 500 -permuteBatch " on librispeech dataset, but I still get the same training error on every...

Hi, we've been experimenting TTS in two setups: 1) tacotron2 for mel-spectrogram + vocoder (4-speaker) 2) tacotron2 for linear-spectrogram (directly, without post-net) + griffin-lim (4-speaker) 1) sounds better than 2),...

for "bits" parameter in hparams.py

1

Hi, Thanks for the great work! If I'm using 25-bit precision audio files for training data, should I set "bits" parameter as 25 in hparams.py file? or does this parameter...

pretrained model for mixture2clean_dnn?

3

Hi ! Thanks for the great work, I found that there is pretrained model for clean2clean_verify, and it works well for my custom wave samples. But why don't you share...

No module named builtins

1

I'm executing 'python train.py --manifest train:train-clean-100/train100manifest.csv --manifest val:dev-clean/devcleanmanifest.csv -e 1 -z 128' on 'neon' directory, but i constantly get the same error: 'No module named builtins'. I've already tried: sudo...

which cuda and cudnn version did you use?

3

when I run ./MetricGAN.py, I get some number (maybe loss) and error, just like this: How do I fix this error? which cuda & cudnn versions did you use? (The...

What was pesq score of deep feature loss and SERGAN?

3

Hi, thanks for sharing your great work! could you elaborate on the numbers that are not listed here? I wanna exactly compare which model performs the best. Thanks! 

where do I get the dataset?

9

I wanna run this code on my server, but I don't know where I can download ComParE2017 dataset. Could you write a link for it??