Mercurial > hg > auditok
changeset 385:edcc102fb33f
Update documentation and configuration
| author | Amine Sehili <amine.sehili@gmail.com> |
|---|---|
| date | Tue, 02 Mar 2021 20:10:50 +0100 |
| parents | c030134b7870 |
| children | 059599823c34 |
| files | .pre-commit-config.yaml CHANGELOG auditok/core.py auditok/util.py doc/_static/css/custom_style.css doc/conf.py doc/examples.rst pyproject.toml |
| diffstat | 8 files changed, 51 insertions(+), 49 deletions(-) [+] |
line wrap: on
line diff
--- a/.pre-commit-config.yaml Mon Mar 01 23:11:49 2021 +0100 +++ b/.pre-commit-config.yaml Tue Mar 02 20:10:50 2021 +0100 @@ -1,6 +1,6 @@ repos: - repo: https://github.com/psf/black - rev: stable + rev: 20.8b1 hooks: - id: black language_version: python3.7
--- a/CHANGELOG Mon Mar 01 23:11:49 2021 +0100 +++ b/CHANGELOG Tue Mar 02 20:10:50 2021 +0100 @@ -10,6 +10,7 @@ - Choose which channel(s) to use for tokenization - Save multi-channel audio data - Refactor code in all modules +- Use genty for tests - Improve documentation - Use ArgumentParser instead of OptionParser in command-line script - Clean up command-line script and move functions and workers to dedicated modules
--- a/auditok/core.py Mon Mar 01 23:11:49 2021 +0100 +++ b/auditok/core.py Tue Mar 02 20:10:50 2021 +0100 @@ -240,9 +240,7 @@ validator = AudioEnergyValidator( energy_threshold, source.sw, source.ch, use_channel=use_channel ) - mode = ( - StreamTokenizer.DROP_TRAILING_SILENCE if drop_trailing_silence else 0 - ) + mode = StreamTokenizer.DROP_TRAILING_SILENCE if drop_trailing_silence else 0 if strict_min_dur: mode |= StreamTokenizer.STRICT_MIN_LENGTH min_length = _duration_to_nb_windows(min_dur, analysis_window, math.ceil) @@ -532,8 +530,7 @@ class _AudioRegionMetadata(dict): - """A class to store `AudioRegion`'s metadata. - """ + """A class to store `AudioRegion`'s metadata.""" def __getattr__(self, name): if name in self: @@ -610,8 +607,7 @@ @meta.setter def meta(self, new_meta): - """Meta data of audio region. - """ + """Meta data of audio region.""" self._meta = _AudioRegionMetadata(new_meta) @classmethod @@ -658,8 +654,7 @@ @property def millis(self): - """A view to slice audio region by milliseconds (using ``region.millis[start:end]``). - """ + """A view to slice audio region by milliseconds (using ``region.millis[start:end]``).""" return self._millis_view @property @@ -673,38 +668,32 @@ @property def sampling_rate(self): - """Samling rate of audio data. - """ + """Samling rate of audio data.""" return self._sampling_rate @property def sr(self): - """Samling rate of audio data, alias for `sampling_rate`. - """ + """Samling rate of audio data, alias for `sampling_rate`.""" return self._sampling_rate @property def sample_width(self): - """Number of bytes per sample, one channel considered. - """ + """Number of bytes per sample, one channel considered.""" return self._sample_width @property def sw(self): - """Number of bytes per sample, alias for `sampling_rate`. - """ + """Number of bytes per sample, alias for `sampling_rate`.""" return self._sample_width @property def channels(self): - """Number of channels of audio data. - """ + """Number of channels of audio data.""" return self._channels @property def ch(self): - """Number of channels of audio data, alias for `channels`. - """ + """Number of channels of audio data, alias for `channels`.""" return self._channels def play(self, progress_bar=False, player=None, **progress_bar_kwargs): @@ -730,9 +719,7 @@ self._data, progress_bar=progress_bar, **progress_bar_kwargs ) - def save( - self, file, audio_format=None, exists_ok=True, **audio_parameters - ): + def save(self, file, audio_format=None, exists_ok=True, **audio_parameters): """ Save audio region to file. @@ -918,8 +905,7 @@ @property def samples(self): - """Audio region as arrays of samples, one array per channel. - """ + """Audio region as arrays of samples, one array per channel.""" if self._samples is None: self._samples = signal.to_array( self._data, self.sample_width, self.channels @@ -1005,9 +991,7 @@ def __truediv__(self, n): if not isinstance(n, int) or n <= 0: - raise TypeError( - "AudioRegion can only be divided by a positive int" - ) + raise TypeError("AudioRegion can only be divided by a positive int") samples_per_sub_region, rest = divmod(len(self), n) onset = 0 sub_regions = [] @@ -1232,9 +1216,7 @@ ) if min_length <= 0 or min_length > max_length: - err_msg = ( - "'min_length' must be > 0 and <= 'max_length' (value={0})" - ) + err_msg = "'min_length' must be > 0 and <= 'max_length' (value={0})" raise ValueError(err_msg.format(min_length)) if max_continuous_silence >= max_length:
--- a/auditok/util.py Mon Mar 01 23:11:49 2021 +0100 +++ b/auditok/util.py Tue Mar 02 20:10:50 2021 +0100 @@ -509,9 +509,7 @@ "asrc", None ) kwargs["fn"] = kwargs.pop("filename", None) or kwargs.pop("fn", None) - kwargs["db"] = kwargs.pop("data_buffer", None) or kwargs.pop( - "db", None - ) + kwargs["db"] = kwargs.pop("data_buffer", None) or kwargs.pop("db", None) record = kwargs.pop("record", False) if not record:
--- a/doc/_static/css/custom_style.css Mon Mar 01 23:11:49 2021 +0100 +++ b/doc/_static/css/custom_style.css Tue Mar 02 20:10:50 2021 +0100 @@ -1,3 +1,7 @@ +div.wy-side-nav-search { + background-color: #000000; +} + div.wy-side-nav-search .version { color: #DDDDDD; font-weight: bold;
--- a/doc/conf.py Mon Mar 01 23:11:49 2021 +0100 +++ b/doc/conf.py Tue Mar 02 20:10:50 2021 +0100 @@ -137,7 +137,7 @@ html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] html_theme_options = { "logo_only": True, - "style_nav_header_background": "black", + "style_nav_header_background": "#000000", } # Theme options are theme-specific and customize the look and feel of a theme
--- a/doc/examples.rst Mon Mar 01 23:11:49 2021 +0100 +++ b/doc/examples.rst Tue Mar 02 20:10:50 2021 +0100 @@ -1,5 +1,5 @@ -Loading audio data ------------------- +Load audio data +--------------- Audio data is loaded with the :func:`load` function which can read from audio files, the microphone or use raw audio data. @@ -7,15 +7,15 @@ From a file =========== -If the first argument of :func:`load` is a string, it should be a path to an audio -file. +If the first argument of :func:`load` is a string, it should be a path to an +audio file. .. code:: python import auditok region = auditok.load("audio.ogg") -If input file contains a raw (headerless) audio data, passing `audio_format="raw"` +If input file contains raw (headerless) audio data, passing `audio_format="raw"` and other audio parameters (`sampling_rate`, `sample_width` and `channels`) is mandatory. In the following example we pass audio parameters with their short names: @@ -42,6 +42,8 @@ data = b"\0" * sr * sw * ch region = auditok.load(data, sr=sr, sw=sw, ch=ch) print(region) + # alternatively you can use + #region = auditok.AudioRegion(data, sr, sw, ch) output: @@ -74,15 +76,30 @@ Skip part of audio data ======================= -If the `skip` parameter is > 0, :func:`load` will skip that leading amount of audio -data: +If the `skip` parameter is > 0, :func:`load` will skip that amount in seconds +of leading audio data: .. code:: python import auditok region = auditok.load("audio.ogg", skip=2) # skip the first 2 seconds -This argument must be 0 when reading from the microphone. +This argument must be 0 when reading data from the microphone. + + +Limit the amount of read audio +============================== + +If the `max_read` parameter is > 0, :func:`load` will read at most that amount +in seconds of audio data: + +.. code:: python + + import auditok + region = auditok.load("audio.ogg", max_read=5) + assert region.duration <= 5 + +This argument is mandatory when reading data from the microphone. Basic split example @@ -188,8 +205,8 @@ seconds with the `max_read` argument. -Accessing recorded data after split ------------------------------------ +Access recorded data after split +-------------------------------- Using a :class:`Recorder` object you can get hold of acquired audio data: @@ -362,7 +379,7 @@ assert len(samples) == region.channels -If `numpy` is not installed you can use: +If `numpy` is installed you can use: .. code:: python