wnhsu / speechvae Goto Github PK

Great thanks for sharing the code. I have a question about the range of log-likelihood to expect with respect to TIMIT data. I am getting inbetween range(-200,-400) for Filter bank features. Thank you for your help.

./local/spec_data_prep.sh: stage 4, generate dataset.cfg
steps/make_dataset_conf.sh /home/ideabay/Documents/vivek/Thesis/SpeechVAE/egs/timit/data/spec_scp/train /home/ideabay/Documents/vivek/Thesis/SpeechVAE/egs/timit/data/spec_scp/dev /home/ideabay/Documents/vivek/Thesis/SpeechVAE/egs/timit/data/spec_scp/test /home/ideabay/Documents/vivek/Thesis/SpeechVAE/egs/timit/data/spec_scp/train/dataset.cfg
steps/make_dataset_conf.sh: /../../../../../SpeechVAE/egs/timit/data/spec_scp/train/feats.scp not found

The linked paper mentions using only magnitude spectrum however the code uses both magnitude and phase.Any reasons?

In the make_dataset.conf file, flags are beig counted as args so total args come out to be 36.Hence the code enters $# -ne 4 and exits.

No file name parse_options.sh.
What is the purpose of this file? It is used at six places but not committed.
Please help.
Thanks

Hi, I read your paper and it said the sequence of features of each sentence is splitted into 80 (or 200) frame chunks. Each chunk is an input "image" for the Convolution VAE. I guess for each sentence, the number of chunks is equal to the number of frames. I'm looking for the script where you split each sentence into "images" but I couldn't find it in the repo. I know it can be a simple function but it will be very helpful for me. Where can I find the part in your repo?
Thanks

Error : path.sh: No such file or directory
I see this error, and there is no such file also in the mentioned directory. So what would be missing?

Any help is appreciated.