docu updated
This commit is contained in:
ortizcruz
Vendored
+113
-23
@@ -16,6 +16,8 @@
|
||||
<script src="_static/doctools.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="autotranscript.app package" href="autotranscript.app.html" />
|
||||
<link rel="prev" title="app module" href="app.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
@@ -40,6 +42,10 @@
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="autotranscript.app.html">autotranscript.app package</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="autotranscript.app.html#submodules">Submodules</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="autotranscript.app.html#module-autotranscript.app.gradio_app">autotranscript.app.gradio_app module</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="autotranscript.app.html#gradio-audio-transcription-app">Gradio Audio Transcription App.</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="autotranscript.app.html#module-autotranscript.app.qtfaststart">autotranscript.app.qtfaststart module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="autotranscript.app.html#module-autotranscript.app">Module contents</a></li>
|
||||
</ul>
|
||||
@@ -215,6 +221,54 @@ get_audio_file: Gets an audio file as an AudioProcessor object.</p>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.AutoTranscribe.__repr__">
|
||||
<span class="sig-name descname"><span class="pre">__repr__</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.__repr__" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Return repr(self).</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.AutoTranscribe.autotranscribe">
|
||||
<span class="sig-name descname"><span class="pre">autotranscribe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">numpy.ndarray</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_original</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.transcript_exporter.Transcript" title="autotranscript.transcript_exporter.Transcript"><span class="pre">Transcript</span></a></span></span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.autotranscribe" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Transcribes an audio file using the whisper model and pyannote diarization model.</p>
|
||||
<dl>
|
||||
<dt>Args:</dt><dd><dl class="simple">
|
||||
<dt>audio_file (Union[str, torch.Tensor, ndarray]): </dt><dd><p>Path to audio file or a tensor representing the audio.</p>
|
||||
</dd>
|
||||
<dt>remove_original (bool, optional): If True, the original audio file will</dt><dd><p>be removed after transcription.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<p><a href="#id3"><span class="problematic" id="id4">*</span></a>args: Additional positional arguments for diarization and transcription.
|
||||
<a href="#id5"><span class="problematic" id="id6">**</span></a>kwargs: Additional keyword arguments for diarization and transcription.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><dl class="simple">
|
||||
<dt>Transcript: A Transcript object containing the transcription,</dt><dd><p>which can be exported to different formats.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.AutoTranscribe.diarization">
|
||||
<span class="sig-name descname"><span class="pre">diarization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">numpy.ndarray</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">dict</span></span></span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.diarization" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Perform diarization on an audio file using the pyannote diarization model.</p>
|
||||
<dl class="simple">
|
||||
<dt>Args:</dt><dd><dl class="simple">
|
||||
<dt>audio_file (Union[str, torch.Tensor, ndarray]):</dt><dd><p>The audio source which can either be a path to the audio file or a tensor representation.</p>
|
||||
</dd>
|
||||
<dt><a href="#id7"><span class="problematic" id="id8">**</span></a>kwargs: </dt><dd><p>Additional keyword arguments for diarization.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><dl class="simple">
|
||||
<dt>dict: </dt><dd><p>A dictionary containing the results of the diarization process.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.AutoTranscribe.get_audio_file">
|
||||
<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_audio_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">numpy.ndarray</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.audio.AudioProcessor" title="autotranscript.audio.AudioProcessor"><span class="pre">AudioProcessor</span></a></span></span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.get_audio_file" title="Permalink to this definition">¶</a></dt>
|
||||
@@ -224,8 +278,8 @@ get_audio_file: Gets an audio file as an AudioProcessor object.</p>
|
||||
<dt>audio_file (Union[str, torch.Tensor, ndarray]): Path to the audio file or </dt><dd><p>a tensor representing the audio.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<p><a href="#id3"><span class="problematic" id="id4">*</span></a>args: Additional positional arguments.
|
||||
<a href="#id5"><span class="problematic" id="id6">**</span></a>kwargs: Additional keyword arguments.</p>
|
||||
<p><a href="#id9"><span class="problematic" id="id10">*</span></a>args: Additional positional arguments.
|
||||
<a href="#id11"><span class="problematic" id="id12">**</span></a>kwargs: Additional keyword arguments.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><dl class="simple">
|
||||
<dt>AudioProcessor: An object containing the waveform and sample rate in</dt><dd><p>torch.Tensor format.</p>
|
||||
@@ -251,20 +305,18 @@ shred (bool, optional): If True, the audio file will be shredded,</p>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.AutoTranscribe.transcribe">
|
||||
<span class="sig-name descname"><span class="pre">transcribe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">numpy.ndarray</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_original</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.transcript_exporter.Transcript" title="autotranscript.transcript_exporter.Transcript"><span class="pre">Transcript</span></a></span></span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.transcribe" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Transcribes an audio file using the whisper model and pyannote diarization model.</p>
|
||||
<dl>
|
||||
<span class="sig-name descname"><span class="pre">transcribe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">numpy.ndarray</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#autotranscript.autotranscript.AutoTranscribe.transcribe" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Transcribe the provided audio file.</p>
|
||||
<dl class="simple">
|
||||
<dt>Args:</dt><dd><dl class="simple">
|
||||
<dt>audio_file (Union[str, torch.Tensor, ndarray]): </dt><dd><p>Path to audio file or a tensor representing the audio.</p>
|
||||
<dt>audio_file (Union[str, torch.Tensor, ndarray]):</dt><dd><p>The audio source, which can either be a path or a tensor representation.</p>
|
||||
</dd>
|
||||
<dt>remove_original (bool, optional): If True, the original audio file will</dt><dd><p>be removed after transcription.</p>
|
||||
<dt><a href="#id13"><span class="problematic" id="id14">**</span></a>kwargs: </dt><dd><p>Additional keyword arguments for transcription.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<p><a href="#id7"><span class="problematic" id="id8">*</span></a>args: Additional positional arguments for diarization and transcription.
|
||||
<a href="#id9"><span class="problematic" id="id10">**</span></a>kwargs: Additional keyword arguments for diarization and transcription.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><dl class="simple">
|
||||
<dt>Transcript: A Transcript object containing the transcription,</dt><dd><p>which can be exported to different formats.</p>
|
||||
<dt>str:</dt><dd><p>The transcribed text from the audio source.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd>
|
||||
@@ -273,9 +325,17 @@ shred (bool, optional): If True, the audio file will be shredded,</p>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
</section>
|
||||
<section id="module-autotranscript.cli">
|
||||
<span id="autotranscript-cli-module"></span><h2>autotranscript.cli module<a class="headerlink" href="#module-autotranscript.cli" title="Permalink to this heading">¶</a></h2>
|
||||
<p>Command-Line Interface (CLI) for the AutoTranscribe class,
|
||||
allowing for user interaction to transcribe and diarize audio files.
|
||||
The function includes arguments for specifying the audio files, model paths,
|
||||
output formats, and other options necessary for transcription.</p>
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="autotranscript.autotranscript.cli">
|
||||
<span class="sig-name descname"><span class="pre">cli</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#autotranscript.autotranscript.cli" title="Permalink to this definition">¶</a></dt>
|
||||
<dt class="sig sig-object py" id="autotranscript.cli.cli">
|
||||
<span class="sig-name descname"><span class="pre">cli</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#autotranscript.cli.cli" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Command-Line Interface (CLI) for the AutoTranscribe class, allowing for user interaction to transcribe
|
||||
and diarize audio files. The function includes arguments for specifying the audio files, model paths,
|
||||
output formats, and other options necessary for transcription.</p>
|
||||
@@ -283,7 +343,6 @@ output formats, and other options necessary for transcription.</p>
|
||||
user-friendly way to access the AutoTranscribe class functionalities.</p>
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
</section>
|
||||
<section id="module-autotranscript.diarisation">
|
||||
<span id="autotranscript-diarisation-module"></span><h2>autotranscript.diarisation module<a class="headerlink" href="#module-autotranscript.diarisation" title="Permalink to this heading">¶</a></h2>
|
||||
@@ -372,7 +431,7 @@ to the diarization process.</p>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.diarisation.Diariser.load_model">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/pyannote/config.yaml'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_token</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_dir</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">Path</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/pyannote'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hparams_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Path</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">pyannote.audio.Pipeline</span></span></span><a class="headerlink" href="#autotranscript.diarisation.Diariser.load_model" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/pyannote/config.yaml'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_auth_token</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_token</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_dir</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">Path</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/pyannote'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hparams_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Path</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">pyannote.audio.Pipeline</span></span></span><a class="headerlink" href="#autotranscript.diarisation.Diariser.load_model" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Loads a pretrained model from pyannote.audio,
|
||||
either from a local cache or online repository.</p>
|
||||
<dl>
|
||||
@@ -383,7 +442,9 @@ either from a local cache or online repository.</p>
|
||||
<p>token: Optional HUGGINGFACE_TOKEN for authenticated access.
|
||||
cache_token: Whether to cache the token locally for future use.
|
||||
cache_dir: Directory for caching models.
|
||||
hparams_file: Path to a YAML file containing hyperparameters.</p>
|
||||
hparams_file: Path to a YAML file containing hyperparameters.
|
||||
args: Additional arguments only to avoid errors.
|
||||
kwargs: Additional keyword arguments only to avoid errors.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><p>Pipeline: A pyannote.audio Pipeline object, encapsulating the loaded model.</p>
|
||||
</dd>
|
||||
@@ -483,9 +544,9 @@ the load_model method for available options.</p>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.transcriber.Transcriber.load_model">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'medium'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">download_root</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/whisper'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.device</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_memory</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.transcriber.Transcriber" title="autotranscript.transcriber.Transcriber"><span class="pre">Transcriber</span></a></span></span><a class="headerlink" href="#autotranscript.transcriber.Transcriber.load_model" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'medium'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">download_root</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'/home/ortizcruzc/.cache/torch/models/whisper'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.device</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_memory</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.transcriber.Transcriber" title="autotranscript.transcriber.Transcriber"><span class="pre">Transcriber</span></a></span></span><a class="headerlink" href="#autotranscript.transcriber.Transcriber.load_model" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Load whisper model.</p>
|
||||
<dl class="simple">
|
||||
<dl>
|
||||
<dt>Args:</dt><dd><dl class="simple">
|
||||
<dt>model (str): Whisper model. Available models include:</dt><dd><ul class="simple">
|
||||
<li><p>‘tiny.en’</p></li>
|
||||
@@ -508,6 +569,8 @@ the load_model method for available options.</p>
|
||||
<dt>in_memory (bool, optional): Whether to load model in memory. </dt><dd><p>Defaults to False.</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<p>args: Additional arguments only to avoid errors.
|
||||
kwargs: Additional keyword arguments only to avoid errors.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><p>Transcriber: A Transcriber object initialized with the specified model.</p>
|
||||
</dd>
|
||||
@@ -533,8 +596,8 @@ save_path (str): The path to save the transcript.</p>
|
||||
<dd><p>Transcribe an audio file.</p>
|
||||
<dl>
|
||||
<dt>Args:</dt><dd><p>audio (Union[str, Tensor, nparray]): The audio file to transcribe.
|
||||
<a href="#id11"><span class="problematic" id="id12">*</span></a>args: Additional arguments.
|
||||
<a href="#id13"><span class="problematic" id="id14">**</span></a>kwargs: Additional keyword arguments,</p>
|
||||
<a href="#id15"><span class="problematic" id="id16">*</span></a>args: Additional arguments.
|
||||
<a href="#id17"><span class="problematic" id="id18">**</span></a>kwargs: Additional keyword arguments,</p>
|
||||
<blockquote>
|
||||
<div><p>such as the language of the audio file.</p>
|
||||
</div></blockquote>
|
||||
@@ -601,7 +664,7 @@ contain speaker and segment information.</p>
|
||||
<dt>Args:</dt><dd><p>args (list): List of speaker names. These will be mapped sequentially to the speakers.
|
||||
kwargs (dict): Dictionary with speaker names as keys and list of segments as values.</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><p>dict: Dictionary with speaker names as keys and the corresponding annotation as values.</p>
|
||||
<dt>Returns:</dt><dd><p>dict: Dictionary with speaker names as keys and list of segments as values.</p>
|
||||
</dd>
|
||||
<dt>Raises:</dt><dd><dl class="simple">
|
||||
<dt>ValueError: If the number of speaker names does not match the number </dt><dd><p>of speakers, or if an unknown speaker is found.</p>
|
||||
@@ -611,6 +674,18 @@ kwargs (dict): Dictionary with speaker names as keys and list of segments as val
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.transcript_exporter.Transcript.from_json">
|
||||
<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">json</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">dict</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#autotranscript.transcript_exporter.Transcript" title="autotranscript.transcript_exporter.Transcript"><span class="pre">Transcript</span></a></span></span><a class="headerlink" href="#autotranscript.transcript_exporter.Transcript.from_json" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Load transcript from json file</p>
|
||||
<dl class="simple">
|
||||
<dt>Args:</dt><dd><p>path (str): path to json file</p>
|
||||
</dd>
|
||||
<dt>Returns:</dt><dd><p>Transcript: Transcript object</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.transcript_exporter.Transcript.get_dict">
|
||||
<span class="sig-name descname"><span class="pre">get_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">dict</span></span></span><a class="headerlink" href="#autotranscript.transcript_exporter.Transcript.get_dict" title="Permalink to this definition">¶</a></dt>
|
||||
@@ -641,7 +716,7 @@ kwargs (dict): Dictionary with speaker names as keys and list of segments as val
|
||||
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="autotranscript.transcript_exporter.Transcript.get_json">
|
||||
<span class="sig-name descname"><span class="pre">get_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">str</span></span></span><a class="headerlink" href="#autotranscript.transcript_exporter.Transcript.get_json" title="Permalink to this definition">¶</a></dt>
|
||||
<span class="sig-name descname"><span class="pre">get_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_annotation</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">str</span></span></span><a class="headerlink" href="#autotranscript.transcript_exporter.Transcript.get_json" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Get transcript as json string
|
||||
:return: transcript as json string
|
||||
:rtype: str</p>
|
||||
@@ -677,8 +752,8 @@ MD, HTML, TEX, and PDF. The file format is determined by the extension of
|
||||
the path.</p>
|
||||
<dl class="simple">
|
||||
<dt>Args:</dt><dd><p>path (str): Path to save the file, including the desired file extension.
|
||||
<a href="#id15"><span class="problematic" id="id16">*</span></a>args: Additional positional arguments to be passed to the specific save methods.
|
||||
<a href="#id17"><span class="problematic" id="id18">**</span></a>kwargs: Additional keyword arguments to be passed to the specific save methods.</p>
|
||||
<a href="#id19"><span class="problematic" id="id20">*</span></a>args: Additional positional arguments to be passed to the specific save methods.
|
||||
<a href="#id21"><span class="problematic" id="id22">**</span></a>kwargs: Additional keyword arguments to be passed to the specific save methods.</p>
|
||||
</dd>
|
||||
<dt>Raises:</dt><dd><p>ValueError: If the file format specified in the path is unknown.</p>
|
||||
</dd>
|
||||
@@ -784,11 +859,26 @@ the path.</p>
|
||||
|
||||
|
||||
<h3>Navigation</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="modules.html">autotranscript</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="app.html">app module</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">autotranscript package</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="setup.html">setup module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="test_autotranscript.html">test_autotranscript module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="transcribe.html">transcribe module</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="modules.html">autotranscript</a><ul>
|
||||
<li>Previous: <a href="app.html" title="previous chapter">app module</a></li>
|
||||
<li>Next: <a href="autotranscript.app.html" title="next chapter">autotranscript.app package</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
Reference in New Issue
Block a user