Skip to content
This repository has been archived by the owner on Aug 3, 2021. It is now read-only.

Commit

Permalink
Merge pull request #169 from Kipok/dev0.4
Browse files Browse the repository at this point in the history
Docs rebuilt
  • Loading branch information
Kipok committed Jun 29, 2018
2 parents 9983266 + e4b1c32 commit e03dbf6
Show file tree
Hide file tree
Showing 66 changed files with 6,615 additions and 2,198 deletions.
154 changes: 152 additions & 2 deletions docs/html/_modules/data/image2label/image2label.html

Large diffs are not rendered by default.

45 changes: 16 additions & 29 deletions docs/html/_modules/data/image2label/imagenet_preprocessing.html

Large diffs are not rendered by default.

45 changes: 29 additions & 16 deletions docs/html/_modules/data/speech2text/speech2text.html

Large diffs are not rendered by default.

27 changes: 23 additions & 4 deletions docs/html/_modules/data/speech2text/speech_utils.html
Original file line number Diff line number Diff line change
Expand Up @@ -197,6 +197,13 @@ <h1>Source code for data.speech2text.speech_utils</h1><div class="highlight"><pr
<span class="p">)</span></div>


<div class="viewcode-block" id="normalize_signal"><a class="viewcode-back" href="../../../api-docs/data.speech2text.html#data.speech2text.speech_utils.normalize_signal">[docs]</a><span class="k">def</span> <span class="nf">normalize_signal</span><span class="p">(</span><span class="n">signal</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Normalize float32 signal to [-1, 1] range</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">signal</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">signal</span><span class="p">))</span></div>


<div class="viewcode-block" id="augment_audio_signal"><a class="viewcode-back" href="../../../api-docs/data.speech2text.html#data.speech2text.speech_utils.augment_audio_signal">[docs]</a><span class="k">def</span> <span class="nf">augment_audio_signal</span><span class="p">(</span><span class="n">signal</span><span class="p">,</span> <span class="n">fs</span><span class="p">,</span> <span class="n">augmentation</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Function that performs audio signal augmentation.</span>

Expand All @@ -208,7 +215,7 @@ <h1>Source code for data.speech2text.speech_utils</h1><div class="highlight"><pr
<span class="sd"> Returns:</span>
<span class="sd"> np.array: np.array with augmented audio signal.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">signal_float</span> <span class="o">=</span> <span class="n">signal</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span> <span class="o">/</span> <span class="mf">32768.0</span>
<span class="n">signal_float</span> <span class="o">=</span> <span class="n">normalize_signal</span><span class="p">(</span><span class="n">signal</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">))</span>

<span class="k">if</span> <span class="n">augmentation</span><span class="p">[</span><span class="s1">&#39;time_stretch_ratio&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="c1"># time stretch (might be slow)</span>
Expand All @@ -227,7 +234,7 @@ <h1>Source code for data.speech2text.speech_utils</h1><div class="highlight"><pr
<span class="n">signal_float</span> <span class="o">+=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">signal_float</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">*</span> \
<span class="mf">10.0</span> <span class="o">**</span> <span class="p">(</span><span class="n">noise_level_db</span> <span class="o">/</span> <span class="mf">20.0</span><span class="p">)</span>

<span class="k">return</span> <span class="p">(</span><span class="n">signal_float</span> <span class="o">*</span> <span class="mf">32768.0</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">)</span></div>
<span class="k">return</span> <span class="p">(</span><span class="n">normalize_signal</span><span class="p">(</span><span class="n">signal_float</span><span class="p">)</span> <span class="o">*</span> <span class="mf">32767.0</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">)</span></div>


<div class="viewcode-block" id="get_speech_features"><a class="viewcode-back" href="../../../api-docs/data.speech2text.html#data.speech2text.speech_utils.get_speech_features">[docs]</a><span class="k">def</span> <span class="nf">get_speech_features</span><span class="p">(</span><span class="n">signal</span><span class="p">,</span> <span class="n">fs</span><span class="p">,</span> <span class="n">num_features</span><span class="p">,</span> <span class="n">pad_to</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
Expand Down Expand Up @@ -273,7 +280,7 @@ <h1>Source code for data.speech2text.speech_utils</h1><div class="highlight"><pr
<span class="k">if</span> <span class="n">pad_to</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">if</span> <span class="n">length</span> <span class="o">%</span> <span class="n">pad_to</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">pad_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pad_to</span> <span class="o">-</span> <span class="n">length</span> <span class="o">%</span> <span class="n">pad_to</span><span class="p">)</span> <span class="o">*</span> <span class="n">n_window_stride</span>
<span class="n">signal</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">pad</span><span class="p">(</span><span class="n">signal</span><span class="p">,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">pad_size</span><span class="p">),</span> <span class="n">mode</span><span class="o">=</span><span class="s1">&#39;reflect&#39;</span><span class="p">)</span>
<span class="n">signal</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">pad</span><span class="p">(</span><span class="n">signal</span><span class="p">,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">pad_size</span><span class="p">),</span> <span class="n">mode</span><span class="o">=</span><span class="s1">&#39;constant&#39;</span><span class="p">)</span>

<span class="k">if</span> <span class="n">features_type</span> <span class="o">==</span> <span class="s1">&#39;spectrogram&#39;</span><span class="p">:</span>
<span class="n">frames</span> <span class="o">=</span> <span class="n">psf</span><span class="o">.</span><span class="n">sigproc</span><span class="o">.</span><span class="n">framesig</span><span class="p">(</span><span class="n">sig</span><span class="o">=</span><span class="n">signal</span><span class="p">,</span>
Expand Down Expand Up @@ -301,10 +308,22 @@ <h1>Source code for data.speech2text.speech_utils</h1><div class="highlight"><pr
<span class="n">preemph</span><span class="o">=</span><span class="mf">0.97</span><span class="p">,</span>
<span class="n">ceplifter</span><span class="o">=</span><span class="mi">2</span><span class="o">*</span><span class="n">num_features</span><span class="p">,</span>
<span class="n">appendEnergy</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>

<span class="k">elif</span> <span class="n">features_type</span> <span class="o">==</span> <span class="s1">&#39;logfbank&#39;</span><span class="p">:</span>
<span class="n">features</span> <span class="o">=</span> <span class="n">psf</span><span class="o">.</span><span class="n">logfbank</span><span class="p">(</span><span class="n">signal</span><span class="o">=</span><span class="n">signal</span><span class="p">,</span>
<span class="n">samplerate</span><span class="o">=</span><span class="n">fs</span><span class="p">,</span>
<span class="n">winlen</span><span class="o">=</span><span class="n">window_size</span><span class="p">,</span>
<span class="n">winstep</span><span class="o">=</span><span class="n">window_stride</span><span class="p">,</span>
<span class="n">nfilt</span><span class="o">=</span><span class="n">num_features</span><span class="p">,</span>
<span class="n">nfft</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span>
<span class="n">lowfreq</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">highfreq</span><span class="o">=</span><span class="n">fs</span><span class="o">/</span><span class="mi">2</span><span class="p">,</span>
<span class="n">preemph</span><span class="o">=</span><span class="mf">0.97</span><span class="p">)</span>

<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Unknown features type: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">features_type</span><span class="p">))</span>

<span class="k">assert</span> <span class="n">features</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">%</span> <span class="n">pad_to</span> <span class="o">==</span> <span class="mi">0</span>
<span class="k">if</span> <span class="n">pad_to</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">features</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">%</span> <span class="n">pad_to</span> <span class="o">==</span> <span class="mi">0</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">features</span><span class="p">)</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">features</span><span class="p">)</span>
<span class="n">features</span> <span class="o">=</span> <span class="p">(</span><span class="n">features</span> <span class="o">-</span> <span class="n">m</span><span class="p">)</span> <span class="o">/</span> <span class="n">s</span>
Expand Down
Loading

0 comments on commit e03dbf6

Please sign in to comment.