This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ################################################################################ | |
| # sox cheat sheet | |
| ################################################################################ | |
| # Example commands for the sox command-line audio processing tool, | |
| # for manipulating or batch processing audio files. | |
| ################################################################################ | |
| # Daniel Jones <[email protected]> | |
| ################################################################################ | |
| ################################################################################ |
chao-ji
/ beamsearch_decoder.py
Last active
October 21, 2024 21:44
Easy to understand implementation of beam search algorithm used in decoder of seq2seq models
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """NumPy implementation of Beam Search. Can be used for decoding in Seq2Seq | |
| models or transformer. | |
| See https://chao-ji.github.io/jekyll/update/2019/01/24/Beam_Search.html | |
| for an in-depth disucssion. | |
| """ | |
| import numpy as np | |
| NEG_INF = -1e9 |
tdomhan
/ coef_weight_plot.py
Created
September 8, 2013 18:16
plotting the largest weights of a L2 regularized classifier + their names
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import matplotlib.pyplot as plt | |
| import numpy as np | |
| figsize(20,8) | |
| #clf is a sklearn classifier e.g. clf = LogisticRegression() | |
| #vecotorizer is a sklearn vectorizer, e.g. vectorizer = TfidfVectorizer() | |
| #let's get the coefficients: | |
| coef = clf.coef_.ravel() | |
| important = np.argsort(np.abs(coef))[-100:] |