reference url: https://scipy-lectures.org/packages/scikit-learn/auto_examples/plot_tsne.html

from matplotlib import pyplot as plt

plt.figure(figsize=(6, 5))

from sklearn.manifold import TSNE

tsne = TSNE(n_components=2, random_state=0) # I can not really undearstand 3-D images..

#a=list

a=np.array(a)

a.shape #(N, n)

b = tsne.fit_transform(a)

b.shape #(N, 2)

for bb in b:

plt.scatter(bb[0], bb[1])

plt.show()

'엄마는 할머니되지마~나계속 이렇게 있을게~'- 큰딸

오늘은 일찍 퇴근해야겠다.

from https://www.youtube.com/watch?v=2Kawrd5szHE

"Videos of this quality on this subject are a rare occurrence . Great job!"

#!/bin/bash

#0. prep using kaldi script

#spk2utt, utt2spk

#wav.scp

#1. fbank for all utterance + utt2spk

compute-fbank-feats --num-mel-bins=80 --sample-frequency=16000 --use-log-fbank=True scp:wav.scp ark:- | add-deltas ark:- ark,scp:feats.ark,feats.scp

#2. cmvn using fbank feats and utt2spk

compute-cmvn-stats --spk2utt=ark:spk2utt scp:feats.scp ark,scp:cmvn.ark,cmvn.scp

apply-cmvn --utt2spk=ark:utt2spk scp:cmvn.scp scp:feats.scp ark,scp:normed_feats.ark,normed_feat.scp

#3. save cmvn applied fbanks to npy

copy-feats scp:normed_feat.scp ark,t:normed_feats.txt

python3 parsing.py normed_feats.txt

parsing.py

import os

import sys

import numpy as np

feat_path = open(sys.argv[1])

status = 0

utt_id = ""

feats = ""

idx = 0

for line in feat_path:

  if status == 0 and "[" in line:

    idx += 1

    print(idx)

    utt_id = line.strip().split()[0]

    status = 1

  elif status == 1:

    feats += line.replace("]","").strip() + "

"

    if "]" in line:

      with open(utt_id + ".npy.txt","w") as npy_file:

        npy_file.write(feats.strip())

      np.save(utt_id + ".npy", np.loadtxt(utt_id + ".npy.txt"))

      os.remove(utt_id + ".npy.txt")

      status = 0

      feats = ""

      utt_id = ""

feat_path.close()