beginner_source/audio_feature_augmentation_tutorial.py [15:70]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
print(torch.__version__)
print(torchaudio.__version__)

######################################################################
# Preparing data and utility functions (skip this section)
# --------------------------------------------------------
#

#@title Prepare data and utility functions. {display-mode: "form"}
#@markdown
#@markdown You do not need to look into this cell.
#@markdown Just execute once and you are good to go.
#@markdown
#@markdown In this tutorial, we will use a speech data from [VOiCES dataset](https://iqtlabs.github.io/voices/), which is licensed under Creative Commos BY 4.0.

#-------------------------------------------------------------------------------
# Preparation of data and helper functions.
#-------------------------------------------------------------------------------

import os
import requests

import librosa
import matplotlib.pyplot as plt


_SAMPLE_DIR = "_sample_data"

SAMPLE_WAV_SPEECH_URL = "https://pytorch-tutorial-assets.s3.amazonaws.com/VOiCES_devkit/source-16k/train/sp0307/Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042.wav"
SAMPLE_WAV_SPEECH_PATH = os.path.join(_SAMPLE_DIR, "speech.wav")

os.makedirs(_SAMPLE_DIR, exist_ok=True)

def _fetch_data():
  uri = [
    (SAMPLE_WAV_SPEECH_URL, SAMPLE_WAV_SPEECH_PATH),
  ]
  for url, path in uri:
    with open(path, 'wb') as file_:
      file_.write(requests.get(url).content)

_fetch_data()

def _get_sample(path, resample=None):
  effects = [
    ["remix", "1"]
  ]
  if resample:
    effects.extend([
      ["lowpass", f"{resample // 2}"],
      ["rate", f'{resample}'],
    ])
  return torchaudio.sox_effects.apply_effects_file(path, effects=effects)

def get_speech_sample(*, resample=None):
  return _get_sample(SAMPLE_WAV_SPEECH_PATH, resample=resample)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



beginner_source/audio_feature_extractions_tutorial.py [33:90]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
print(torch.__version__)
print(torchaudio.__version__)

######################################################################
# Preparing data and utility functions (skip this section)
# --------------------------------------------------------
#

#@title Prepare data and utility functions. {display-mode: "form"}
#@markdown
#@markdown You do not need to look into this cell.
#@markdown Just execute once and you are good to go.
#@markdown
#@markdown In this tutorial, we will use a speech data from [VOiCES dataset](https://iqtlabs.github.io/voices/), which is licensed under Creative Commos BY 4.0.

#-------------------------------------------------------------------------------
# Preparation of data and helper functions.
#-------------------------------------------------------------------------------

import os
import requests

import librosa
import matplotlib.pyplot as plt
from IPython.display import Audio, display


_SAMPLE_DIR = "_sample_data"

SAMPLE_WAV_SPEECH_URL = "https://pytorch-tutorial-assets.s3.amazonaws.com/VOiCES_devkit/source-16k/train/sp0307/Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042.wav"
SAMPLE_WAV_SPEECH_PATH = os.path.join(_SAMPLE_DIR, "speech.wav")

os.makedirs(_SAMPLE_DIR, exist_ok=True)


def _fetch_data():
  uri = [
    (SAMPLE_WAV_SPEECH_URL, SAMPLE_WAV_SPEECH_PATH),
  ]
  for url, path in uri:
    with open(path, 'wb') as file_:
      file_.write(requests.get(url).content)

_fetch_data()

def _get_sample(path, resample=None):
  effects = [
    ["remix", "1"]
  ]
  if resample:
    effects.extend([
      ["lowpass", f"{resample // 2}"],
      ["rate", f'{resample}'],
    ])
  return torchaudio.sox_effects.apply_effects_file(path, effects=effects)

def get_speech_sample(*, resample=None):
  return _get_sample(SAMPLE_WAV_SPEECH_PATH, resample=resample)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -