make project relaease ready

setup.cfg

@@ -0,0 +1,31 @@
+[metadata]
+name = scraibe
+version = attr: scraibe.__version__
+author = Jacob Schmieder
+author_email = Jacob.Schmieder@dbfz.de
+description = My package description
+long_description = file: README.md, LICENSE
+platforms = Linux
+keywords = transcription speech recognition whisper pyannote audio speech-to-text speech-to-text transcription speech-to-text recognition voice-to-speech
+license = GPL-3.0
+classifiers =
+    Development Status :: 3 - Alpha
+    Environment :: GPU :: NVIDIA CUDA :: 11.2
+    License :: OSI Approved :: Open Software License 3.0 (OSL-3.0)
+    Topic :: Scientific/Engineering :: Artificial Intelligence
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+
+[options]
+zip_safe = False
+include_package_data = True
+packages = find:
+python_requires = >=3.7
+install_requires =
+    requests
+    importlib-metadata; python_version<"3.8"
+
+[options.entry_points]
+console_scripts =
+    executable-name = scraibe.cli:cli

setup.py

@@ -1,3 +1,4 @@
+from calendar import c
 import pkg_resources
 import os
 from setuptools import setup, find_packages
@@ -36,11 +37,24 @@ if __name__ == "__main__":
             'https://download.pytorch.org/whl/cu113',
             ],
         url= github_url,
-        license='',
+        
+        license='GPL-3',
         author='Jacob Schmieder',
         author_email='Jacob.Schmieder@dbfz.de',
         description='Transcription tool for audio files based on Whisper and Pyannote',
+        classifiers=[
+            'Development Status :: 3 - Alpha',
+            'Environment :: GPU :: NVIDIA CUDA :: 11.2',
+            'License :: OSI Approved :: Open Software License 3.0 (OSL-3.0)',
+            'Topic :: Scientific/Engineering :: Artificial Intelligence',
+            'Programming Language :: Python :: 3.8',
+            'Programming Language :: Python :: 3.9',
+            'Programming Language :: Python :: 3.10'],
+        keywords = ['transcription', 'speech recognition', 'whisper', 'pyannote', 'audio',
+                    'speech-to-text', 'speech-to-text transcription', 'speech-to-text recognition',
+                    'voice-to-speech'],
         package_data={ "header" : ["app/header.html"], "logo" : ["app/Logo_KIDA_bmel_green.svg"]},
         entry_points={'console_scripts':
             ['scraibe = scraibe.cli:cli']}
+        
     )

test_autotranscript.py

@@ -1,120 +0,0 @@
-import pytest
-from scraibe import Transcriber
-from unittest.mock import patch, mock_open
-import os
-
-def test_load_pyannote_model():
-    """
-    Test load_pyannote_test
-    """
-    from pyannote.audio.pipelines.speaker_diarization import SpeakerDiarization
-    from pyannote.audio import Pipeline
-
-    pipeline = Pipeline.from_pretrained("models/pyannote/speaker_diarization/config.yaml")
-    assert isinstance(pipeline, SpeakerDiarization)
-
-# Test Transcribtion class
-
-
-@pytest.fixture
-def transcriber():
-    """
-    Prepare Transcriber for testing
-    Returns: Transcriber Object
-    """
-
-    return Transcriber.load_model("medium", local=True)
-
-
-def test_Transcriber_init(transcriber):
-    """
-    Test Transcriber initialization with a whisper model 
-    """
-    
-    assert isinstance(transcriber, Transcriber)
-
-def test_transcription(transcriber):
-    """
-    Test transcription
-    """
-
-    transcript = transcriber.transcribe("tests/test.wav") 
-    assert isinstance(transcript, str)
-    
-def test_save_transcript_to_file(transcriber):
-    """
-    Test save_transcript_to_file
-    """
-    transcript = transcriber.transcribe("tests/test.wav")
-
-    Transcriber.save_transcript(transcript, "tests/output.txt")
-    
-    assert os.path.exists("tests/output.txt")
-
-    os.remove("tests/output.txt")
-    
-# Test Diaraization class
-
-from scraibe import Diariser
-
-@pytest.fixture
-def diarisation():
-    """
-    Prepare Diarisation for testing
-    Returns: Diarisation Object
-    """
-
-    return Diariser.load_model("models/pyannote/speaker_diarization/config.yaml", local=True)
-
-def test_Diarisation_init(diarisation):
-    """
-    Test Diarisation initialization with a pyannote model 
-    """
-    
-    assert isinstance(diarisation, Diariser)
-
-def test_diarisation(diarisation):
-    """
-    Test diarisation
-    """
-
-    diarisation = diarisation.diarization("tests/test.wav") 
-    assert isinstance(diarisation, dict)
-
-# Test AudioProcessor
-
-from scraibe import AudioProcessor , TorchAudioProcessor
-
-
-def test_AudioProcessor_init():
-    """
-    Test AudioProcessor initialization
-    """
-    audio = AudioProcessor("tests/test.wav")
-    assert isinstance(audio, AudioProcessor)
-
-def test_AudioProcessor_convert():
-    """
-    Test AudioProcessor convert
-    """
-    audio = AudioProcessor("tests/test.wav")
-    audio.convert_audio("tests/test.mp3", format="mp3")
-    assert os.path.exists("tests/test.mp3")
-    
-def test_TorchAudioProcessor_from_file():
-    """
-    Test TorchAudioProcessor initialization
-    """
-    audio = TorchAudioProcessor.from_file("tests/test.wav")
-    
-    assert isinstance(audio, TorchAudioProcessor)
-    
-    os.remove("tests/test.mp3")
-
-
-def test_TorchAudioProcessor_from_ffmpeg():
-    """
-    Test TorchAudioProcessor initialization
-    """
-    audio = TorchAudioProcessor.from_ffmpeg("tests/test.wav")
-    assert isinstance(audio, TorchAudioProcessor)