You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/third_party/python_kaldi_features/example.py

30 lines
1.3 KiB

E2E/Streaming Transformer/Conformer ASR (#578) * add cmvn and label smoothing loss layer * add layer for transformer * add glu and conformer conv * add torch compatiable hack, mask funcs * not hack size since it exists * add test; attention * add attention, common utils, hack paddle * add audio utils * conformer batch padding mask bug fix #223 * fix typo, python infer fix rnn mem opt name error and batchnorm1d, will be available at 2.0.2 * fix ci * fix ci * add encoder * refactor egs * add decoder * refactor ctc, add ctc align, refactor ckpt, add warmup lr scheduler, cmvn utils * refactor docs * add fix * fix readme * fix bugs, refactor collator, add pad_sequence, fix ckpt bugs * fix docstring * refactor data feed order * add u2 model * refactor cmvn, test * add utils * add u2 config * fix bugs * fix bugs * fix autograd maybe has problem when using inplace operation * refactor data, build vocab; add format data * fix text featurizer * refactor build vocab * add fbank, refactor feature of speech * refactor audio feat * refactor data preprare * refactor data * model init from config * add u2 bins * flake8 * can train * fix bugs, add coverage, add scripts * test can run * fix data * speed perturb with sox * add spec aug * fix for train * fix train logitc * fix logger * log valid loss, time dataset process * using np for speed perturb, remove some debug log of grad clip * fix logger * fix build vocab * fix logger name * using module logger as default * fix * fix install * reorder imports * fix board logger * fix logger * kaldi fbank and mfcc * fix cmvn and print prarams * fix add_eos_sos and cmvn * fix cmvn compute * fix logger and cmvn * fix subsampling, label smoothing loss, remove useless * add notebook test * fix log * fix tb logger * multi gpu valid * fix log * fix log * fix config * fix compute cmvn, need paddle 2.1 * add cmvn notebook * fix layer tools * fix compute cmvn * add rtf * fix decoding * fix layer tools * fix log, add avg script * more avg and test info * fix dataset pickle problem; using 2.1 paddle; num_workers can > 0; ckpt save in exp dir;fix setup.sh; * add vimrc * refactor tiny script, add transformer and stream conf * spm demo; librisppech scripts and confs * fix log * add librispeech scripts * refactor data pipe; fix conf; fix u2 default params * fix bugs * refactor aishell scripts * fix test * fix cmvn * fix s0 scripts * fix ds2 scripts and bugs * fix dev & test dataset filter * fix dataset filter * filter dev * fix ckpt path * filter test, since librispeech will cause OOM, but all test wer will be worse, since mismatch train with test * add comment * add syllable doc * fix ds2 configs * add doc * add pypinyin tools * fix decoder using blank_id=0 * mmseg with pybind11 * format code
4 years ago
#!/usr/bin/env python
from python_speech_features import mfcc
from python_speech_features import delta
from python_speech_features import logfbank
import scipy.io.wavfile as wav
(rate,sig) = wav.read("english.wav")
# note that generally nfilt=40 is used for speech recognition
fbank_feat = logfbank(sig,nfilt=23,lowfreq=20,dither=0,wintype='povey')
# the computed fbank coefficents of english.wav with dimension [110,23]
# [ 12.2865 12.6906 13.1765 15.714 16.064 15.7553 16.5746 16.9205 16.6472 16.1302 16.4576 16.7326 16.8864 17.7215 18.88 19.1377 19.1495 18.6683 18.3886 20.3506 20.2772 18.8248 18.1899
# 11.9198 13.146 14.7215 15.8642 17.4288 16.394 16.8238 16.1095 16.4297 16.6331 16.3163 16.5093 17.4981 18.3429 19.6555 19.6263 19.8435 19.0534 19.001 20.0287 19.7707 19.5852 19.1112
# ...
# ...
# the same with that using kaldi commands: compute-fbank-feats --dither=0.0
mfcc_feat = mfcc(sig,dither=0,useEnergy=True,wintype='povey')
# the computed mfcc coefficents of english.wav with dimension [110,13]
# [ 17.1337 -23.3651 -7.41751 -7.73686 -21.3682 -8.93884 -3.70843 4.68346 -16.0676 12.782 -7.24054 8.25089 10.7292
# 17.1692 -23.3028 -5.61872 -4.0075 -23.287 -20.6101 -5.51584 -6.15273 -14.4333 8.13052 -0.0345329 2.06274 -0.564298
# ...
# ...
# the same with that using kaldi commands: compute-mfcc-feats --dither=0.0