db06038d90d4af330086c6c95f0249bad865f73c,corpus/librispeech.py,LibriDataset,__init__,#LibriDataset#Any#Any#Any#Any#,22

Before Change


        
        // Read text
        text = Parallel(n_jobs=-1)(delayed(read_text)(str(f)) for f in file_list)
        text = Parallel(n_jobs=-1)(delayed(tokenizer.encode)(txt) for txt in text)
        
        // Read file size and sort dataset by file size (Note: feature len. may be different)
        file_len = Parallel(n_jobs=-1)(delayed(getsize)(f) for f in file_list)
        self.file_list, self.text = zip(*[(f_name,txt) \

After Change


        // Read text
        text = Parallel(n_jobs=READ_FILE_THREADS)(delayed(read_text)(str(f)) for f in file_list)
        //text = Parallel(n_jobs=-1)(delayed(tokenizer.encode)(txt) for txt in text)
        text = [tokenizer.encode(txt) for txt in text]
        
        // Read file size and sort dataset by file size (Note: feature len. may be different)
        file_len = Parallel(n_jobs=READ_FILE_THREADS)(delayed(getsize)(f) for f in file_list)
        self.file_list, self.text = zip(*[(f_name,txt) \
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 9

Instances


Project Name: Alexander-H-Liu/End-to-end-ASR-Pytorch
Commit Name: db06038d90d4af330086c6c95f0249bad865f73c
Time: 2019-08-20
Author: alexliu36@gmail.com
File Name: corpus/librispeech.py
Class Name: LibriDataset
Method Name: __init__


Project Name: Alexander-H-Liu/End-to-end-ASR-Pytorch
Commit Name: db06038d90d4af330086c6c95f0249bad865f73c
Time: 2019-08-20
Author: alexliu36@gmail.com
File Name: corpus/librispeech.py
Class Name: LibriTextDataset
Method Name: __init__


Project Name: automl/auto-sklearn
Commit Name: 830822b2364affa37d87fa62e487873cb44c2bf4
Time: 2020-10-06
Author: feurerm@informatik.uni-freiburg.de
File Name: scripts/03_calculate_metafeatures.py
Class Name:
Method Name: