diff --git a/docs/_build/doctrees/app.doctree b/docs/_build/doctrees/app.doctree index aa46bd2..3f7ebc9 100644 Binary files a/docs/_build/doctrees/app.doctree and b/docs/_build/doctrees/app.doctree differ diff --git a/docs/_build/doctrees/autotranscript.app.doctree b/docs/_build/doctrees/autotranscript.app.doctree index b575367..7d0ba12 100644 Binary files a/docs/_build/doctrees/autotranscript.app.doctree and b/docs/_build/doctrees/autotranscript.app.doctree differ diff --git a/docs/_build/doctrees/autotranscript.doctree b/docs/_build/doctrees/autotranscript.doctree index 30b4488..4549e3f 100644 Binary files a/docs/_build/doctrees/autotranscript.doctree and b/docs/_build/doctrees/autotranscript.doctree differ diff --git a/docs/_build/doctrees/environment.pickle b/docs/_build/doctrees/environment.pickle index 9e37e4b..46bf7a1 100644 Binary files a/docs/_build/doctrees/environment.pickle and b/docs/_build/doctrees/environment.pickle differ diff --git a/docs/_build/doctrees/gradio_app.doctree b/docs/_build/doctrees/gradio_app.doctree deleted file mode 100644 index 492a136..0000000 Binary files a/docs/_build/doctrees/gradio_app.doctree and /dev/null differ diff --git a/docs/_build/doctrees/index.doctree b/docs/_build/doctrees/index.doctree index fcc4695..5755e28 100644 Binary files a/docs/_build/doctrees/index.doctree and b/docs/_build/doctrees/index.doctree differ diff --git a/docs/_build/doctrees/modules.doctree b/docs/_build/doctrees/modules.doctree index 387e742..7ff31b6 100644 Binary files a/docs/_build/doctrees/modules.doctree and b/docs/_build/doctrees/modules.doctree differ diff --git a/docs/_build/doctrees/setup.doctree b/docs/_build/doctrees/setup.doctree index 7ea34fd..ffe1050 100644 Binary files a/docs/_build/doctrees/setup.doctree and b/docs/_build/doctrees/setup.doctree differ diff --git a/docs/_build/doctrees/test_autotranscript.doctree b/docs/_build/doctrees/test_autotranscript.doctree index b1fbb19..8f89d15 100644 Binary files a/docs/_build/doctrees/test_autotranscript.doctree and b/docs/_build/doctrees/test_autotranscript.doctree differ diff --git a/docs/_build/doctrees/transcribe.doctree b/docs/_build/doctrees/transcribe.doctree index 0cbf0b0..1e9833f 100644 Binary files a/docs/_build/doctrees/transcribe.doctree and b/docs/_build/doctrees/transcribe.doctree differ diff --git a/docs/_build/html/_sources/autotranscript.app.rst.txt b/docs/_build/html/_sources/autotranscript.app.rst.txt index ee68a6f..16b4b88 100644 --- a/docs/_build/html/_sources/autotranscript.app.rst.txt +++ b/docs/_build/html/_sources/autotranscript.app.rst.txt @@ -4,6 +4,14 @@ autotranscript.app package Submodules ---------- +autotranscript.app.gradio\_app module +------------------------------------- + +.. automodule:: autotranscript.app.gradio_app + :members: + :undoc-members: + :show-inheritance: + autotranscript.app.qtfaststart module ------------------------------------- diff --git a/docs/_build/html/_sources/autotranscript.rst.txt b/docs/_build/html/_sources/autotranscript.rst.txt index 5ba3195..f220d9a 100644 --- a/docs/_build/html/_sources/autotranscript.rst.txt +++ b/docs/_build/html/_sources/autotranscript.rst.txt @@ -28,6 +28,14 @@ autotranscript.autotranscript module :undoc-members: :show-inheritance: +autotranscript.cli module +------------------------- + +.. automodule:: autotranscript.cli + :members: + :undoc-members: + :show-inheritance: + autotranscript.diarisation module --------------------------------- diff --git a/docs/_build/html/_sources/gradio_app.rst.txt b/docs/_build/html/_sources/gradio_app.rst.txt deleted file mode 100644 index bafaed0..0000000 --- a/docs/_build/html/_sources/gradio_app.rst.txt +++ /dev/null @@ -1,7 +0,0 @@ -gradio\_app module -================== - -.. automodule:: gradio_app - :members: - :undoc-members: - :show-inheritance: diff --git a/docs/_build/html/_sources/index.rst.txt b/docs/_build/html/_sources/index.rst.txt index 0033a97..924ab4d 100644 --- a/docs/_build/html/_sources/index.rst.txt +++ b/docs/_build/html/_sources/index.rst.txt @@ -1,14 +1,14 @@ -.. AutoTranscript documentation master file, created by - sphinx-quickstart on Thu Aug 31 08:17:31 2023. +.. ScrAIbe documentation master file, created by + sphinx-quickstart on Mon Sep 18 18:17:08 2023. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. -Welcome to AutoTranscript's documentation! -========================================== +Welcome to ScrAIbe's documentation! +=================================== -`AutoTranscript`: Fully Automated Transcription using AI +`ScrAIbe` is a state-of-the-art, PyTorch based multilingual speech-to-text framework to generate fully automated transcriptions. -`AutoTranscript` is a PyTorch based interface speech-to-text tool to generate fully automated transcriptions. AutoTranscript uses AI models containing speaker diarization models: +Beyond transcription, ScrAIbe supports advanced functions, such as speaker diarization and speaker recognition. .. toctree:: @@ -19,9 +19,3 @@ Welcome to AutoTranscript's documentation! -Indices and tables -================== - -* :ref:`genindex` -* :ref:`modindex` -* :ref:`search` diff --git a/docs/_build/html/_sources/modules.rst.txt b/docs/_build/html/_sources/modules.rst.txt index b1fd70c..f715b46 100644 --- a/docs/_build/html/_sources/modules.rst.txt +++ b/docs/_build/html/_sources/modules.rst.txt @@ -6,7 +6,6 @@ autotranscript app autotranscript - gradio_app setup test_autotranscript transcribe diff --git a/docs/_build/html/app.html b/docs/_build/html/app.html index 8e0f6fa..b54328e 100644 --- a/docs/_build/html/app.html +++ b/docs/_build/html/app.html @@ -16,6 +16,8 @@ + + @@ -63,11 +65,26 @@

Navigation

+

Contents:

+

Related Topics

diff --git a/docs/_build/html/autotranscript.app.html b/docs/_build/html/autotranscript.app.html index 5beafa2..d3b285e 100644 --- a/docs/_build/html/autotranscript.app.html +++ b/docs/_build/html/autotranscript.app.html @@ -16,6 +16,8 @@ + + @@ -37,6 +39,74 @@

Submodules

+
+

autotranscript.app.gradio_app module

+
+

Gradio Audio Transcription App.

+

This module provides an interface to transcribe audio files using the +AutoTranscribe model. Users can either upload an audio file or record their speech +live for transcription. The application supports multiple languages and provides +options to specify the number of speakers and the language of the audio.

+
+
Attributes:

LANGUAGES (list): A list of supported languages for transcription.

+
+
Usage:

Run this script to start the Gradio web interface for audio transcription.

+
+
+
+
+class GradioTranscriptionInterface(model: AutoTranscribe)
+

Bases: object

+

Interface handling the interaction between Gradio UI and the Audio Transcription system.

+
+
+__init__(model: AutoTranscribe)
+

Initializes the GradioTranscriptionInterface with a transcription model.

+
+
Args:

model (AutoTranscribe): Model responsible for audio transcription tasks.

+
+
+
+ +
+
+auto_transcribe(source, num_speakers: int, translation: bool, language: str)
+

Shortcut method for the AutoTranscribe task.

+
+
Returns:

tuple: Transcribed text (str), JSON output (dict)

+
+
+
+ +
+
+perform_diarisation(source, num_speakers)
+

Shortcut method for the Diarisation task.

+
+
Returns:

str: JSON output of diarisation result.

+
+
+
+ +
+
+transcribe(source, translation, language)
+

Shortcut method for the Transcribe task.

+
+
Returns:

str: Transcribed text.

+
+
+
+ +
+ +
+
+gradio_Interface(model: AutoTranscribe = None)
+
+ +
+

autotranscript.app.qtfaststart module

This file contains a modified version of qtfaststart by qtfaststart @@ -185,11 +255,28 @@ like “ftyp” or “moov”.

Navigation

+

Contents:

+

Related Topics

diff --git a/docs/_build/html/autotranscript.html b/docs/_build/html/autotranscript.html index 302040a..0766505 100644 --- a/docs/_build/html/autotranscript.html +++ b/docs/_build/html/autotranscript.html @@ -16,6 +16,8 @@ + + @@ -40,6 +42,10 @@
+ +
+

autotranscript.cli module

+

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.

-
-cli()
+
+cli()

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.

@@ -283,7 +343,6 @@ output formats, and other options necessary for transcription.

user-friendly way to access the AutoTranscribe class functionalities.

-

autotranscript.diarisation module

@@ -372,7 +431,7 @@ to the diarization process.

-classmethod load_model(model: str = '/home/ortizcruzc/.cache/torch/models/pyannote/config.yaml', token: str = None, cache_token: bool = False, cache_dir: Union[Path, str] = '/home/ortizcruzc/.cache/torch/models/pyannote', hparams_file: Union[str, Path] = None) → pyannote.audio.Pipeline
+classmethod load_model(model: str = '/home/ortizcruzc/.cache/torch/models/pyannote/config.yaml', use_auth_token: str = None, cache_token: bool = True, cache_dir: Union[Path, str] = '/home/ortizcruzc/.cache/torch/models/pyannote', hparams_file: Union[str, Path] = None, *args, **kwargs) → pyannote.audio.Pipeline

Loads a pretrained model from pyannote.audio, either from a local cache or online repository.

@@ -383,7 +442,9 @@ either from a local cache or online repository.

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.

+hparams_file: Path to a YAML file containing hyperparameters. +args: Additional arguments only to avoid errors. +kwargs: Additional keyword arguments only to avoid errors.

Returns:

Pipeline: A pyannote.audio Pipeline object, encapsulating the loaded model.

@@ -483,9 +544,9 @@ the load_model method for available options.

-classmethod load_model(model: str = 'medium', download_root: str = '/home/ortizcruzc/.cache/torch/models/whisper', device: Optional[Union[str, torch.device]] = None, in_memory: bool = False) → Transcriber
+classmethod load_model(model: str = 'medium', download_root: str = '/home/ortizcruzc/.cache/torch/models/whisper', device: Optional[Union[str, torch.device]] = None, in_memory: bool = False, *args, **kwargs) → Transcriber

Load whisper model.

-
+
Args:
model (str): Whisper model. Available models include:

  • ‘tiny.en’

    • @@ -508,6 +569,8 @@ the load_model method for available options.

    in_memory (bool, optional): Whether to load model in memory.

    Defaults to False.

+

args: Additional arguments only to avoid errors. +kwargs: Additional keyword arguments only to avoid errors.

Returns:

Transcriber: A Transcriber object initialized with the specified model.

@@ -533,8 +596,8 @@ save_path (str): The path to save the transcript.

Transcribe an audio file.

Args:

audio (Union[str, Tensor, nparray]): The audio file to transcribe. -*args: Additional arguments. -**kwargs: Additional keyword arguments,

+*args: Additional arguments. +**kwargs: Additional keyword arguments,

such as the language of the audio file.

@@ -601,7 +664,7 @@ contain speaker and segment information.

Args:

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.

-
Returns:

dict: Dictionary with speaker names as keys and the corresponding annotation as values.

+
Returns:

dict: Dictionary with speaker names as keys and list of segments as values.

Raises:
ValueError: If the number of speaker names does not match the number

of speakers, or if an unknown speaker is found.

@@ -611,6 +674,18 @@ kwargs (dict): Dictionary with speaker names as keys and list of segments as val
+
+
+classmethod from_json(json: Union[dict, str]) → Transcript
+

Load transcript from json file

+
+
Args:

path (str): path to json file

+
+
Returns:

Transcript: Transcript object

+
+
+
+
get_dict() → dict
@@ -641,7 +716,7 @@ kwargs (dict): Dictionary with speaker names as keys and list of segments as val
-get_json(*args, **kwargs) → str
+get_json(*args, use_annotation: bool = True, **kwargs) → str

Get transcript as json string :return: transcript as json string :rtype: str

@@ -677,8 +752,8 @@ MD, HTML, TEX, and PDF. The file format is determined by the extension of the path.

Args:

path (str): Path to save the file, including the desired file extension. -*args: Additional positional arguments to be passed to the specific save methods. -**kwargs: Additional keyword arguments to be passed to the specific save methods.

+*args: Additional positional arguments to be passed to the specific save methods. +**kwargs: Additional keyword arguments to be passed to the specific save methods.

Raises:

ValueError: If the file format specified in the path is unknown.

@@ -784,11 +859,26 @@ the path.

Navigation

+

Contents:

+

Related Topics

diff --git a/docs/_build/html/genindex.html b/docs/_build/html/genindex.html index 2afa676..21fe6b3 100644 --- a/docs/_build/html/genindex.html +++ b/docs/_build/html/genindex.html @@ -60,6 +60,8 @@
  • (AutoTranscribe method)
  • (Diariser method) +
    • +
  • (GradioTranscriptionInterface method)
  • (Transcriber method)
    • @@ -72,6 +74,8 @@ + +
    • autotranscript.audio @@ -131,13 +148,18 @@
    • module
    - - - + @@ -235,10 +263,10 @@
  • get_index() (in module autotranscript.app.qtfaststart)
    • - - + @@ -280,12 +312,16 @@
  • autotranscript
  • autotranscript.app +
    • +
  • autotranscript.app.gradio_app
  • autotranscript.app.qtfaststart
  • autotranscript.audio
  • autotranscript.autotranscript +
    • +
  • autotranscript.cli
  • autotranscript.diarisation
    • @@ -313,6 +349,8 @@ + + + + + +
    -
  • gradio_app module
  • setup module
  • test_autotranscript module
  • transcribe module
    • @@ -102,7 +103,6 @@
  • autotranscript
    		•     autotranscript.app
        + autotranscript.app.gradio_app +
        @@ -76,6 +81,11 @@     autotranscript.autotranscript
        + autotranscript.cli +
        diff --git a/docs/_build/html/searchindex.js b/docs/_build/html/searchindex.js index 9b1692d..776da5e 100644 --- a/docs/_build/html/searchindex.js +++ b/docs/_build/html/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["app", "autotranscript", "autotranscript.app", "gradio_app", "index", "modules", "setup", "test_autotranscript", "transcribe"], "filenames": ["app.rst", "autotranscript.rst", "autotranscript.app.rst", "gradio_app.rst", "index.rst", "modules.rst", "setup.rst", "test_autotranscript.rst", "transcribe.rst"], "titles": ["app module", "autotranscript package", "autotranscript.app package", "gradio_app module", "Welcome to AutoTranscript\u2019s documentation!", "autotranscript", "setup module", "test_autotranscript module", "transcribe module"], "terms": {"parse_cont": 0, "content": [0, 5], "filenam": 0, "date": 0, "update_output": 0, "list_of_cont": 0, "list_of_nam": 0, "list_of_d": 0, "app": [1, 4, 5], "qtfaststart": [1, 5], "thi": [1, 2], "provid": [1, 2], "audioprocessor": 1, "util": 1, "pytorchaudio": 1, "handl": 1, "file": [1, 2], "It": 1, "includ": [1, 2], "function": 1, "load": 1, "cut": 1, "manag": 1, "waveform": 1, "offer": 1, "effici": 1, "flexibl": 1, "process": [1, 2], "avail": 1, "method": [1, 2], "usag": 1, "from": [1, 2], "audio_import": 1, "from_fil": 1, "path": 1, "audiofil": 1, "wav": 1, "cut_waveform": 1, "start": 1, "1": [1, 2], "0": [1, 2], "end": 1, "5": 1, "constant": 1, "sample_r": 1, "int": 1, "default": 1, "sampl": [1, 2], "rate": 1, "normalization_factor": 1, "float": 1, "normal": 1, "factor": 1, "torch": 1, "tensor": 1, "sr": 1, "16000": 1, "arg": 1, "kwarg": 1, "base": [1, 2, 4], "object": 1, "leverag": 1, "attribut": 1, "The": [1, 2], "__init__": 1, "none": 1, "initi": 1, "option": 1, "addit": 1, "argument": 1, "keyword": 1, "e": 1, "g": [1, 2], "devic": 1, "us": [1, 2, 4], "If": [1, 2], "cuda": 1, "rais": [1, 2], "valueerror": 1, "type": [1, 2], "__repr__": [1, 2], "str": 1, "return": [1, 2], "repr": 1, "self": 1, "segment": 1, "between": 1, "specifi": 1, "time": 1, "second": 1, "classmethod": 1, "creat": [1, 2], "an": [1, 2], "instanc": 1, "contain": [1, 2, 4], "static": 1, "load_audio": 1, "open": 1, "read": [1, 2], "mono": 1, "resampl": 1, "necessari": 1, "ensur": 1, "compat": 1, "pyannot": 1, "requir": 1, "ffmpeg": 1, "cli": 1, "desir": 1, "tupl": [1, 2], "A": [1, 2], "numpi": 1, "arrai": 1, "float32": 1, "dtype": 1, "runtimeerror": 1, "fail": 1, "serv": 1, "core": 1, "transcript": [1, 4], "system": 1, "respons": 1, "diariz": [1, 4], "pretrain": 1, "model": [1, 4], "speech": [1, 4], "text": [1, 4], "whisper": 1, "speaker": [1, 4], "access": 1, "interfac": [1, 2, 4], "task": 1, "separ": 1, "timestamp": 1, "By": 1, "encapsul": 1, "complex": 1, "underli": 1, "allow": 1, "straightforward": 1, "integr": 1, "variou": 1, "applic": 1, "rang": 1, "servic": 1, "voic": 1, "assist": 1, "main": 1, "perform": 1, "format": [1, 2], "output": 1, "import": 1, "whisper_model": 1, "dia_model": 1, "union": 1, "bool": 1, "diarisationtyp": 1, "incorpor": 1, "comprehens": 1, "appropri": 1, "remove_audio_fil": 1, "remov": 1, "origin": [1, 2], "avoid": 1, "disk": 1, "space": 1, "issu": 1, "data": 1, "privaci": 1, "get_audio_fil": 1, "get": 1, "itself": 1, "diarisation_model": 1, "audio_fil": 1, "ndarrai": 1, "torchaudioprocessor": 1, "repres": 1, "posit": [1, 2], "shred": 1, "fals": 1, "audio_file_path": 1, "true": 1, "just": 1, "remove_origin": 1, "after": 1, "which": [1, 2], "can": [1, 2], "export": 1, "differ": 1, "command": 1, "line": 1, "user": 1, "interact": 1, "other": [1, 2], "execut": 1, "friendli": 1, "wai": [1, 2], "heart": 1, "identifi": 1, "individu": 1, "given": 1, "token_path": 1, "token": 1, "pyannote_default_path": 1, "pyannote_default_config": 1, "configur": 1, "load_model": 1, "config": 1, "yaml": 1, "diarisation_output": 1, "determin": 1, "who": 1, "spoke": 1, "when": [1, 2], "dict": 1, "annot": 1, "effect": 1, "each": 1, "dictionari": 1, "name": [1, 2], "inform": 1, "relat": 1, "format_diarization_output": 1, "dia": 1, "raw": 1, "more": 1, "usabl": 1, "structur": 1, "project": 1, "represent": [1, 2], "kei": 1, "list": [1, 2], "valu": 1, "home": 1, "ortizcruzc": 1, "cach": 1, "cache_token": 1, "cache_dir": 1, "hparams_fil": 1, "pipelin": 1, "either": 1, "local": 1, "onlin": 1, "repositori": 1, "speaker_diar": 1, "huggingface_token": 1, "authent": 1, "whether": [1, 2], "futur": 1, "directori": 1, "hyperparamet": 1, "config_diarization_yaml": 1, "file_path": 1, "path_to_segment": 1, "updat": 1, "offlin": 1, "manual": 1, "manipul": 1, "filenotfounderror": 1, "found": 1, "tool": [1, 4], "work": 1, "save": 1, "act": 1, "simplifi": 1, "featur": 1, "size": [1, 2], "nparrai": 1, "adapt": 1, "languag": 1, "specif": 1, "control": 1, "verbos": 1, "whisper_default_path": 1, "download": 1, "your_packag": 1, "medium": 1, "save_transcript": 1, "txt": 1, "wrapper": 1, "around": 1, "intricaci": 1, "easi": 1, "_get_whisper_kwarg": 1, "privat": 1, "valid": 1, "exampl": 1, "note": 1, "support": [1, 2], "pleas": 1, "refer": 1, "download_root": 1, "in_memori": 1, "tini": 1, "en": 1, "small": [1, 2], "larg": 1, "v1": 1, "v2": 1, "memori": 1, "save_path": 1, "string": [1, 2], "store": 1, "json": 1, "html": 1, "latex": 1, "should": 1, "correspond": 1, "id": 1, "descript": 1, "__str__": 1, "convert": [1, 2], "stamp": 1, "associ": [1, 2], "These": 1, "map": 1, "sequenti": 1, "number": [1, 2], "doe": [1, 2], "match": 1, "unknown": 1, "get_dict": 1, "get_html": 1, "get_json": 1, "rtype": 1, "get_md": 1, "markdown": 1, "get_tex": 1, "ar": 1, "present": 1, "first": 1, "letter": 1, "alphabet": 1, "md": 1, "tex": 1, "pdf": 1, "extens": 1, "pass": 1, "to_html": 1, "paramet": 1, "to_json": 1, "to_md": 1, "to_pdf": 1, "placehold": 1, "implement": 1, "need": [1, 2], "to_tex": 1, "to_txt": 1, "get_vers": 1, "build_vers": 1, "git_vers": 1, "modifi": 2, "version": [2, 5], "http": 2, "github": 2, "com": 2, "danielgtaylor": 2, "tree": 2, "master": 2, "all": 2, "credit": 2, "goe": 2, "author": 2, "copyright": 2, "c": 2, "2008": 2, "2013": 2, "daniel": 2, "taylor": 2, "dan": 2, "programm": 2, "art": 2, "org": 2, "permiss": 2, "herebi": 2, "grant": 2, "free": 2, "charg": 2, "ani": 2, "person": 2, "obtain": 2, "copi": 2, "softwar": 2, "document": 2, "deal": 2, "without": 2, "restrict": 2, "limit": 2, "right": 2, "merg": 2, "publish": 2, "distribut": 2, "sublicens": 2, "sell": 2, "permit": 2, "whom": 2, "furnish": 2, "do": 2, "so": 2, "subject": 2, "follow": 2, "condit": 2, "abov": 2, "notic": 2, "shall": 2, "substanti": 2, "portion": 2, "THE": 2, "IS": 2, "AS": 2, "warranti": 2, "OF": 2, "kind": 2, "express": 2, "OR": 2, "impli": 2, "BUT": 2, "NOT": 2, "TO": 2, "merchant": 2, "fit": 2, "FOR": 2, "particular": 2, "purpos": 2, "AND": 2, "noninfring": 2, "IN": 2, "NO": 2, "event": 2, "holder": 2, "BE": 2, "liabl": 2, "claim": 2, "damag": 2, "liabil": 2, "action": 2, "contract": 2, "tort": 2, "otherwis": 2, "aris": 2, "out": 2, "connect": 2, "WITH": 2, "class": [2, 5], "atom": 2, "nice": 2, "alia": 2, "field": 2, "2": 2, "except": 2, "faststartexcept": 2, "someth": 2, "bad": 2, "happen": 2, "dure": 2, "faststartsetuperror": 2, "rasis": 2, "ask": 2, "malformedfileerror": 2, "input": 2, "setup": [2, 4, 5], "unexpect": 2, "unsupportedformaterror": 2, "movi": 2, "recogn": 2, "find_atom": 2, "datastream": 2, "compatibilti": 2, "_find_atoms_ex": 2, "get_chunk": 2, "stream": 2, "chunk_siz": 2, "get_index": 2, "index": [2, 4], "top": 2, "level": 2, "absolut": 2, "byte": 2, "ftyp": 2, "24": 2, "moov": 2, "25": 2, "2658": 2, "2683": 2, "8": 2, "element": 2, "order": 2, "thei": 2, "appear": 2, "infilenam": 2, "inf": 2, "quicktim": 2, "mp4": 2, "move": 2, "metadata": 2, "front": 2, "write": 2, "new": 2, "set": 2, "than": 2, "zero": 2, "veri": 2, "full": 2, "header": 2, "bug": 2, "report": 2, "read_atom": 2, "where": 2, "alreadi": 2, "fourcc": 2, "like": 2, "modul": [4, 5], "search": 4, "page": 4, "packag": [4, 5], "subpackag": 5, "submodul": 5, "audio": 5, "processor": 5, "autotranscrib": 5, "diaris": 5, "misc": 5, "transcrib": [4, 5], "transcript_export": 5, "gradio_app": [4, 5], "test_autotranscript": [4, 5], "fulli": 4, "autom": 4, "ai": 4, "pytorch": 4, "gener": 4}, "objects": {"": [[0, 0, 0, "-", "app"], [1, 0, 0, "-", "autotranscript"]], "app": [[0, 1, 1, "", "parse_contents"], [0, 1, 1, "", "update_output"]], "autotranscript": [[2, 0, 0, "-", "app"], [1, 0, 0, "-", "audio"], [1, 0, 0, "-", "autotranscript"], [1, 0, 0, "-", "diarisation"], [1, 0, 0, "-", "misc"], [1, 0, 0, "-", "transcriber"], [1, 0, 0, "-", "transcript_exporter"], [1, 0, 0, "-", "version"]], "autotranscript.app": [[2, 0, 0, "-", "qtfaststart"]], "autotranscript.app.qtfaststart": [[2, 2, 1, "", "Atom"], [2, 5, 1, "", "FastStartException"], [2, 5, 1, "", "FastStartSetupError"], [2, 5, 1, "", "MalformedFileError"], [2, 5, 1, "", "UnsupportedFormatError"], [2, 1, 1, "", "find_atoms"], [2, 1, 1, "", "get_chunks"], [2, 1, 1, "", "get_index"], [2, 1, 1, "", "process"], [2, 1, 1, "", "read_atom"]], "autotranscript.app.qtfaststart.Atom": [[2, 3, 1, "", "__repr__"], [2, 4, 1, "", "name"], [2, 4, 1, "", "position"], [2, 4, 1, "", "size"]], "autotranscript.audio": [[1, 2, 1, "", "AudioProcessor"]], "autotranscript.audio.AudioProcessor": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "cut"], [1, 3, 1, "", "from_file"], [1, 3, 1, "", "load_audio"]], "autotranscript.autotranscript": [[1, 2, 1, "", "AutoTranscribe"], [1, 1, 1, "", "cli"]], "autotranscript.autotranscript.AutoTranscribe": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "get_audio_file"], [1, 3, 1, "", "remove_audio_file"], [1, 3, 1, "", "transcribe"]], "autotranscript.diarisation": [[1, 2, 1, "", "Diariser"]], "autotranscript.diarisation.Diariser": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "diarization"], [1, 3, 1, "", "format_diarization_output"], [1, 3, 1, "", "load_model"]], "autotranscript.misc": [[1, 1, 1, "", "config_diarization_yaml"]], "autotranscript.transcriber": [[1, 2, 1, "", "Transcriber"]], "autotranscript.transcriber.Transcriber": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "load_model"], [1, 3, 1, "", "save_transcript"], [1, 3, 1, "", "transcribe"]], "autotranscript.transcript_exporter": [[1, 2, 1, "", "Transcript"]], "autotranscript.transcript_exporter.Transcript": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "__str__"], [1, 3, 1, "", "annotate"], [1, 3, 1, "", "get_dict"], [1, 3, 1, "", "get_html"], [1, 3, 1, "", "get_json"], [1, 3, 1, "", "get_md"], [1, 3, 1, "", "get_tex"], [1, 3, 1, "", "save"], [1, 3, 1, "", "to_html"], [1, 3, 1, "", "to_json"], [1, 3, 1, "", "to_md"], [1, 3, 1, "", "to_pdf"], [1, 3, 1, "", "to_tex"], [1, 3, 1, "", "to_txt"]], "autotranscript.version": [[1, 1, 1, "", "get_version"], [1, 1, 1, "", "git_version"]]}, "objtypes": {"0": "py:module", "1": "py:function", "2": "py:class", "3": "py:method", "4": "py:attribute", "5": "py:exception"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"], "2": ["py", "class", "Python class"], "3": ["py", "method", "Python method"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "exception", "Python exception"]}, "titleterms": {"app": [0, 2], "modul": [0, 1, 2, 3, 6, 7, 8], "autotranscript": [1, 2, 4, 5], "packag": [1, 2], "subpackag": 1, "submodul": [1, 2], "audio": 1, "processor": 1, "autotranscrib": 1, "class": 1, "diaris": 1, "misc": 1, "transcrib": [1, 8], "transcript_export": 1, "version": 1, "content": [1, 2, 4], "qtfaststart": 2, "gradio_app": 3, "welcom": 4, "s": 4, "document": 4, "indic": 4, "tabl": 4, "setup": 6, "test_autotranscript": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 6, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 56}}) \ No newline at end of file +Search.setIndex({"docnames": ["app", "autotranscript", "autotranscript.app", "index", "modules", "setup", "test_autotranscript", "transcribe"], "filenames": ["app.rst", "autotranscript.rst", "autotranscript.app.rst", "index.rst", "modules.rst", "setup.rst", "test_autotranscript.rst", "transcribe.rst"], "titles": ["app module", "autotranscript package", "autotranscript.app package", "Welcome to ScrAIbe\u2019s documentation!", "autotranscript", "setup module", "test_autotranscript module", "transcribe module"], "terms": {"app": [1, 3, 4], "gradio_app": [1, 4], "qtfaststart": [1, 4], "autotranscript": 3, "packag": [3, 4], "index": 2, "modul": [3, 4], "search": [], "page": [], "subpackag": 4, "submodul": 4, "content": [0, 4], "audio": 4, "cli": 4, "diaris": [2, 4], "misc": 4, "transcrib": [2, 3, 4], "transcript_export": 4, "version": [2, 4], "thi": [1, 2], "provid": [1, 2], "audioprocessor": 1, "util": 1, "pytorchaudio": 1, "handl": [1, 2], "file": [1, 2], "It": 1, "includ": [1, 2], "function": [1, 3], "load": 1, "cut": 1, "manag": 1, "waveform": 1, "offer": 1, "effici": 1, "flexibl": 1, "process": [1, 2], "avail": 1, "method": [1, 2], "usag": [1, 2], "from": [1, 2], "audio_import": 1, "from_fil": 1, "path": 1, "audiofil": 1, "wav": 1, "cut_waveform": 1, "start": [1, 2], "1": [1, 2], "0": [1, 2], "end": 1, "5": 1, "constant": 1, "sample_r": 1, "int": [1, 2], "default": 1, "sampl": [1, 2], "rate": 1, "normalization_factor": 1, "float": 1, "normal": 1, "factor": 1, "torch": 1, "tensor": 1, "sr": 1, "16000": 1, "arg": [1, 2], "kwarg": 1, "base": [1, 2, 3], "object": [1, 2], "leverag": 1, "attribut": [1, 2], "The": [1, 2], "__init__": [1, 2], "none": [1, 2], "initi": [1, 2], "option": [1, 2], "addit": 1, "argument": 1, "keyword": 1, "e": 1, "g": [1, 2], "devic": 1, "us": [1, 2], "If": [1, 2], "cuda": 1, "rais": [1, 2], "valueerror": 1, "type": [1, 2], "__repr__": [1, 2], "str": [1, 2], "return": [1, 2], "repr": 1, "self": 1, "segment": 1, "between": [1, 2], "specifi": [1, 2], "time": 1, "second": 1, "classmethod": 1, "creat": [1, 2], "an": [1, 2], "instanc": 1, "contain": [1, 2], "static": 1, "load_audio": 1, "open": 1, "read": [1, 2], "mono": 1, "resampl": 1, "necessari": 1, "ensur": 1, "compat": 1, "pyannot": 1, "requir": 1, "ffmpeg": 1, "desir": 1, "tupl": [1, 2], "A": [1, 2], "numpi": 1, "arrai": 1, "float32": 1, "dtype": 1, "runtimeerror": 1, "fail": 1, "serv": 1, "core": 1, "transcript": [1, 3], "system": [1, 2], "respons": [1, 2], "diariz": [1, 3], "pretrain": 1, "model": [1, 2], "speech": [1, 2, 3], "text": [1, 2, 3], "whisper": 1, "speaker": [1, 2, 3], "access": 1, "interfac": [1, 2], "task": [1, 2], "separ": 1, "timestamp": 1, "By": 1, "encapsul": 1, "complex": 1, "underli": 1, "allow": 1, "straightforward": 1, "integr": 1, "variou": 1, "applic": [1, 2], "rang": 1, "servic": 1, "voic": 1, "assist": 1, "main": 1, "perform": 1, "format": [1, 2], "output": [1, 2], "import": 1, "whisper_model": 1, "dia_model": 1, "union": 1, "bool": [1, 2], "diarisationtyp": 1, "incorpor": 1, "comprehens": 1, "appropri": 1, "remove_audio_fil": 1, "remov": 1, "origin": [1, 2], "avoid": 1, "disk": 1, "space": 1, "issu": 1, "data": 1, "privaci": 1, "get_audio_fil": 1, "get": 1, "itself": 1, "diarisation_model": 1, "audio_fil": 1, "ndarrai": 1, "remove_origin": 1, "fals": 1, "repres": 1, "true": 1, "after": 1, "posit": [1, 2], "which": [1, 2], "can": [1, 2], "export": 1, "differ": 1, "dict": [1, 2], "sourc": [1, 2], "either": [1, 2], "represent": [1, 2], "dictionari": 1, "result": [1, 2], "torchaudioprocessor": 1, "shred": 1, "audio_file_path": 1, "just": 1, "heart": 1, "identifi": 1, "individu": 1, "given": 1, "token_path": 1, "token": 1, "pyannote_default_path": 1, "pyannote_default_config": 1, "configur": 1, "load_model": 1, "config": 1, "yaml": 1, "diarisation_output": 1, "determin": 1, "who": 1, "spoke": 1, "when": [1, 2], "annot": 1, "effect": 1, "each": 1, "name": [1, 2], "other": [1, 2], "inform": 1, "relat": 1, "format_diarization_output": 1, "dia": 1, "raw": 1, "more": 1, "usabl": 1, "structur": 1, "project": 1, "kei": 1, "list": [1, 2], "valu": 1, "home": 1, "ortizcruzc": 1, "cach": 1, "use_auth_token": 1, "cache_token": 1, "cache_dir": 1, "hparams_fil": 1, "pipelin": 1, "local": 1, "onlin": 1, "repositori": 1, "speaker_diar": 1, "huggingface_token": 1, "authent": 1, "whether": [1, 2], "futur": 1, "directori": 1, "hyperparamet": 1, "onli": 1, "error": 1, "config_diarization_yaml": 1, "file_path": 1, "path_to_segment": 1, "updat": 1, "offlin": 1, "manual": 1, "manipul": 1, "filenotfounderror": 1, "found": 1, "tool": 1, "work": 1, "save": 1, "act": 1, "user": [1, 2], "simplifi": 1, "featur": 1, "size": [1, 2], "nparrai": 1, "adapt": 1, "languag": [1, 2], "specif": 1, "control": 1, "verbos": 1, "whisper_default_path": 1, "download": 1, "your_packag": 1, "medium": 1, "save_transcript": 1, "txt": 1, "wrapper": 1, "around": 1, "intricaci": 1, "easi": 1, "_get_whisper_kwarg": 1, "privat": 1, "valid": 1, "exampl": 1, "note": 1, "support": [1, 2, 3], "pleas": 1, "refer": 1, "download_root": 1, "in_memori": 1, "tini": 1, "en": 1, "small": [1, 2], "larg": 1, "v1": 1, "v2": 1, "memori": 1, "save_path": 1, "string": [1, 2], "store": 1, "json": [1, 2], "html": 1, "latex": 1, "should": 1, "correspond": 1, "id": 1, "descript": 1, "__str__": 1, "convert": [1, 2], "stamp": 1, "associ": [1, 2], "These": 1, "map": 1, "sequenti": 1, "number": [1, 2], "doe": [1, 2], "match": 1, "unknown": 1, "from_json": 1, "get_dict": 1, "get_html": 1, "get_json": 1, "use_annot": 1, "rtype": 1, "get_md": 1, "markdown": 1, "get_tex": 1, "ar": 1, "present": 1, "first": 1, "letter": 1, "alphabet": 1, "md": 1, "tex": 1, "pdf": 1, "extens": 1, "pass": 1, "to_html": 1, "paramet": 1, "to_json": 1, "to_md": 1, "to_pdf": 1, "placehold": 1, "implement": 1, "need": [1, 2], "to_tex": 1, "to_txt": 1, "get_vers": 1, "build_vers": 1, "git_vers": 1, "modifi": 2, "http": 2, "github": 2, "com": 2, "danielgtaylor": 2, "tree": 2, "master": 2, "all": 2, "credit": 2, "goe": 2, "author": 2, "copyright": 2, "c": 2, "2008": 2, "2013": 2, "daniel": 2, "taylor": 2, "dan": 2, "programm": 2, "art": [2, 3], "org": 2, "permiss": 2, "herebi": 2, "grant": 2, "free": 2, "charg": 2, "ani": 2, "person": 2, "obtain": 2, "copi": 2, "softwar": 2, "document": 2, "deal": 2, "without": 2, "restrict": 2, "limit": 2, "right": 2, "merg": 2, "publish": 2, "distribut": 2, "sublicens": 2, "sell": 2, "permit": 2, "whom": 2, "furnish": 2, "do": 2, "so": 2, "subject": 2, "follow": 2, "condit": 2, "abov": 2, "notic": 2, "shall": 2, "substanti": 2, "portion": 2, "THE": 2, "IS": 2, "AS": 2, "warranti": 2, "OF": 2, "kind": 2, "express": 2, "OR": 2, "impli": 2, "BUT": 2, "NOT": 2, "TO": 2, "merchant": 2, "fit": 2, "FOR": 2, "particular": 2, "purpos": 2, "AND": 2, "noninfring": 2, "IN": 2, "NO": 2, "event": 2, "holder": 2, "BE": 2, "liabl": 2, "claim": 2, "damag": 2, "liabil": 2, "action": 2, "contract": 2, "tort": 2, "otherwis": 2, "aris": 2, "out": 2, "connect": 2, "WITH": 2, "class": [2, 4], "atom": 2, "nice": 2, "alia": 2, "field": 2, "2": 2, "except": 2, "faststartexcept": 2, "someth": 2, "bad": 2, "happen": 2, "dure": 2, "faststartsetuperror": 2, "rasis": 2, "ask": 2, "malformedfileerror": 2, "input": 2, "setup": [2, 3, 4], "unexpect": 2, "wai": [1, 2], "unsupportedformaterror": 2, "movi": 2, "recogn": 2, "find_atom": 2, "datastream": 2, "compatibilti": 2, "_find_atoms_ex": 2, "get_chunk": 2, "stream": 2, "chunk_siz": 2, "get_index": 2, "top": 2, "level": 2, "absolut": 2, "byte": 2, "ftyp": 2, "24": 2, "moov": 2, "25": 2, "2658": 2, "2683": 2, "8": 2, "element": 2, "order": 2, "thei": 2, "appear": 2, "infilenam": 2, "inf": 2, "quicktim": 2, "mp4": 2, "move": 2, "metadata": 2, "front": 2, "write": 2, "new": 2, "set": 2, "than": 2, "zero": 2, "veri": 2, "full": 2, "header": 2, "bug": 2, "report": 2, "read_atom": 2, "where": 2, "alreadi": 2, "fourcc": 2, "like": 2, "test_autotranscript": [3, 4], "processor": 4, "autotranscrib": [2, 4], "parse_cont": 0, "filenam": 0, "date": 0, "update_output": 0, "list_of_cont": 0, "list_of_nam": 0, "list_of_d": 0, "gradio": 1, "command": 1, "line": 1, "interact": [1, 2], "execut": 1, "friendli": 1, "upload": 2, "record": 2, "live": 2, "multipl": 2, "run": 2, "script": 2, "web": 2, "gradiotranscriptioninterfac": 2, "ui": 2, "auto_transcrib": 2, "num_speak": 2, "translat": 2, "shortcut": 2, "perform_diaris": 2, "gradio_interfac": 2, "state": 3, "pytorch": 3, "multilingu": 3, "framework": 3, "gener": 3, "fulli": 3, "autom": 3, "beyond": 3, "advanc": 3, "recognit": 3}, "objects": {"": [[0, 0, 0, "-", "app"], [1, 0, 0, "-", "autotranscript"]], "app": [[0, 1, 1, "", "parse_contents"], [0, 1, 1, "", "update_output"]], "autotranscript": [[2, 0, 0, "-", "app"], [1, 0, 0, "-", "audio"], [1, 0, 0, "-", "autotranscript"], [1, 0, 0, "-", "cli"], [1, 0, 0, "-", "diarisation"], [1, 0, 0, "-", "misc"], [1, 0, 0, "-", "transcriber"], [1, 0, 0, "-", "transcript_exporter"], [1, 0, 0, "-", "version"]], "autotranscript.app": [[2, 0, 0, "-", "gradio_app"], [2, 0, 0, "-", "qtfaststart"]], "autotranscript.app.gradio_app": [[2, 2, 1, "", "GradioTranscriptionInterface"], [2, 1, 1, "", "gradio_Interface"]], "autotranscript.app.gradio_app.GradioTranscriptionInterface": [[2, 3, 1, "", "__init__"], [2, 3, 1, "", "auto_transcribe"], [2, 3, 1, "", "perform_diarisation"], [2, 3, 1, "", "transcribe"]], "autotranscript.app.qtfaststart": [[2, 2, 1, "", "Atom"], [2, 5, 1, "", "FastStartException"], [2, 5, 1, "", "FastStartSetupError"], [2, 5, 1, "", "MalformedFileError"], [2, 5, 1, "", "UnsupportedFormatError"], [2, 1, 1, "", "find_atoms"], [2, 1, 1, "", "get_chunks"], [2, 1, 1, "", "get_index"], [2, 1, 1, "", "process"], [2, 1, 1, "", "read_atom"]], "autotranscript.app.qtfaststart.Atom": [[2, 3, 1, "", "__repr__"], [2, 4, 1, "", "name"], [2, 4, 1, "", "position"], [2, 4, 1, "", "size"]], "autotranscript.audio": [[1, 2, 1, "", "AudioProcessor"]], "autotranscript.audio.AudioProcessor": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "cut"], [1, 3, 1, "", "from_file"], [1, 3, 1, "", "load_audio"]], "autotranscript.autotranscript": [[1, 2, 1, "", "AutoTranscribe"]], "autotranscript.autotranscript.AutoTranscribe": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "autotranscribe"], [1, 3, 1, "", "diarization"], [1, 3, 1, "", "get_audio_file"], [1, 3, 1, "", "remove_audio_file"], [1, 3, 1, "", "transcribe"]], "autotranscript.cli": [[1, 1, 1, "", "cli"]], "autotranscript.diarisation": [[1, 2, 1, "", "Diariser"]], "autotranscript.diarisation.Diariser": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "diarization"], [1, 3, 1, "", "format_diarization_output"], [1, 3, 1, "", "load_model"]], "autotranscript.misc": [[1, 1, 1, "", "config_diarization_yaml"]], "autotranscript.transcriber": [[1, 2, 1, "", "Transcriber"]], "autotranscript.transcriber.Transcriber": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "load_model"], [1, 3, 1, "", "save_transcript"], [1, 3, 1, "", "transcribe"]], "autotranscript.transcript_exporter": [[1, 2, 1, "", "Transcript"]], "autotranscript.transcript_exporter.Transcript": [[1, 3, 1, "", "__init__"], [1, 3, 1, "", "__repr__"], [1, 3, 1, "", "__str__"], [1, 3, 1, "", "annotate"], [1, 3, 1, "", "from_json"], [1, 3, 1, "", "get_dict"], [1, 3, 1, "", "get_html"], [1, 3, 1, "", "get_json"], [1, 3, 1, "", "get_md"], [1, 3, 1, "", "get_tex"], [1, 3, 1, "", "save"], [1, 3, 1, "", "to_html"], [1, 3, 1, "", "to_json"], [1, 3, 1, "", "to_md"], [1, 3, 1, "", "to_pdf"], [1, 3, 1, "", "to_tex"], [1, 3, 1, "", "to_txt"]], "autotranscript.version": [[1, 1, 1, "", "get_version"], [1, 1, 1, "", "git_version"]]}, "objtypes": {"0": "py:module", "1": "py:function", "2": "py:class", "3": "py:method", "4": "py:attribute", "5": "py:exception"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"], "2": ["py", "class", "Python class"], "3": ["py", "method", "Python method"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "exception", "Python exception"]}, "titleterms": {"autotranscript": [1, 2, 4], "packag": [1, 2], "subpackag": 1, "submodul": [1, 2], "audio": [1, 2], "modul": [0, 1, 2, 5, 6, 7], "cli": 1, "diaris": 1, "misc": 1, "transcrib": [1, 7], "transcript_export": 1, "version": 1, "content": [1, 2, 3], "app": [0, 2], "gradio_app": 2, "qtfaststart": 2, "welcom": 3, "scraib": 3, "s": 3, "document": 3, "indic": [], "tabl": [], "processor": 1, "autotranscrib": 1, "class": 1, "setup": 5, "test_autotranscript": 6, "gradio": 2, "transcript": 2}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 6, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 56}}) \ No newline at end of file diff --git a/docs/_build/html/setup.html b/docs/_build/html/setup.html index 0761842..3f34e69 100644 --- a/docs/_build/html/setup.html +++ b/docs/_build/html/setup.html @@ -17,7 +17,7 @@ - + @@ -60,7 +60,6 @@
  • autotranscript
    • app module
    • autotranscript package
      • -
    • gradio_app module
    • setup module
    • test_autotranscript module
    • transcribe module
      • @@ -73,7 +72,7 @@
      • Documentation overview
        • diff --git a/docs/_build/html/test_autotranscript.html b/docs/_build/html/test_autotranscript.html index 1aedcf1..7ac2fd9 100644 --- a/docs/_build/html/test_autotranscript.html +++ b/docs/_build/html/test_autotranscript.html @@ -60,7 +60,6 @@
      • autotranscript
        • app module
        • autotranscript package
          • -
        • gradio_app module
        • setup module
        • test_autotranscript module
        • transcribe module
          • diff --git a/docs/_build/html/transcribe.html b/docs/_build/html/transcribe.html index 2d979f2..29baf90 100644 --- a/docs/_build/html/transcribe.html +++ b/docs/_build/html/transcribe.html @@ -59,7 +59,6 @@
        • autotranscript
          • app module
          • autotranscript package
            • -
          • gradio_app module
          • setup module
          • test_autotranscript module
          • transcribe module
            • diff --git a/docs/autotranscript.app.rst b/docs/autotranscript.app.rst index ee68a6f..16b4b88 100644 --- a/docs/autotranscript.app.rst +++ b/docs/autotranscript.app.rst @@ -4,6 +4,14 @@ autotranscript.app package Submodules ---------- +autotranscript.app.gradio\_app module +------------------------------------- + +.. automodule:: autotranscript.app.gradio_app + :members: + :undoc-members: + :show-inheritance: + autotranscript.app.qtfaststart module ------------------------------------- diff --git a/docs/autotranscript.rst b/docs/autotranscript.rst index 5ba3195..f220d9a 100644 --- a/docs/autotranscript.rst +++ b/docs/autotranscript.rst @@ -28,6 +28,14 @@ autotranscript.autotranscript module :undoc-members: :show-inheritance: +autotranscript.cli module +------------------------- + +.. automodule:: autotranscript.cli + :members: + :undoc-members: + :show-inheritance: + autotranscript.diarisation module --------------------------------- diff --git a/docs/conf.py b/docs/conf.py index 61d9ec0..2b5e8af 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -25,7 +25,7 @@ author = 'Jacob Schmieder' # -- General configuration --------------------------------------------------- # Mock unavailable library modules -autodoc_mock_imports = ["dash", "torch", "pytest", "numpy", "tqdm", "pyannote", "yaml", "whisper"] +autodoc_mock_imports = ["dash", "torch", "pytest", "numpy", "tqdm", "pyannote", "yaml", "whisper", "gradio"] # Add any Sphinx extension module names here, as strings. They can be # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom diff --git a/docs/gradio_app.rst b/docs/gradio_app.rst deleted file mode 100644 index bafaed0..0000000 --- a/docs/gradio_app.rst +++ /dev/null @@ -1,7 +0,0 @@ -gradio\_app module -================== - -.. automodule:: gradio_app - :members: - :undoc-members: - :show-inheritance: diff --git a/docs/index.rst b/docs/index.rst index 0033a97..924ab4d 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -1,14 +1,14 @@ -.. AutoTranscript documentation master file, created by - sphinx-quickstart on Thu Aug 31 08:17:31 2023. +.. ScrAIbe documentation master file, created by + sphinx-quickstart on Mon Sep 18 18:17:08 2023. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. -Welcome to AutoTranscript's documentation! -========================================== +Welcome to ScrAIbe's documentation! +=================================== -`AutoTranscript`: Fully Automated Transcription using AI +`ScrAIbe` is a state-of-the-art, PyTorch based multilingual speech-to-text framework to generate fully automated transcriptions. -`AutoTranscript` is a PyTorch based interface speech-to-text tool to generate fully automated transcriptions. AutoTranscript uses AI models containing speaker diarization models: +Beyond transcription, ScrAIbe supports advanced functions, such as speaker diarization and speaker recognition. .. toctree:: @@ -19,9 +19,3 @@ Welcome to AutoTranscript's documentation! -Indices and tables -================== - -* :ref:`genindex` -* :ref:`modindex` -* :ref:`search` diff --git a/docs/modules.rst b/docs/modules.rst index b1fd70c..f715b46 100644 --- a/docs/modules.rst +++ b/docs/modules.rst @@ -6,7 +6,6 @@ autotranscript app autotranscript - gradio_app setup test_autotranscript transcribe