santi-pdp/pase

ASR experiment with custom dataset

zmf0507 opened this issue · 2 comments

zmf0507 commented

I have trained the PASE+ encoder on my custom datatset but I couldnt see anything about data preparation for ASR experiment on custom dataset. I have a set of .wav files and their corresponding text transcript. Can you please tell me how to arrange my dataset so that I cun run run_TIMIT_full_decoding.py for my dataset? I could see in the code that there are label files as well . How are these labels file generated ? Any help will be appreciated

uuwz commented

Hello! I have been replicating this experiment recently, but during the process of making the dataset config file, do I know where to obtain these files. (-- train_scp data/LibriSpeed/libri_tr.scp -- test_scp data/LibriSpeed/libri_te.scp\

--Libri_ Dict data/LibriSpeed/Libri_ Dict. npy). I look forward to your reply very much. Thank you.

uuwz commented

Or how to obtain these three files on a custom dataset. Thank you! Looking forward to your reply.