Add files via upload

autotranscript/__init__.py

@@ -0,0 +1,4 @@
+from autotranscript.__main__ import *
+from autotranscript.version import get_version as _get_version
+
+__version__ = _get_version()

autotranscript/__main__.py

@@ -0,0 +1,126 @@
+
+import whisper
+from time import time
+import os
+from moviepy.editor import *
+from typing import Union
+
+class Transcribe:
+    def __init__(self, audiofile : Union[bool, str, list] = None, model : str =  "medium", language :str =  "German"):
+        """
+         Class to autotranscript audio and video files with the Whisper model
+        :param audiofile: audio file or list of audio files
+        :param model: model to use for transcription
+        :param language: language of the audio file
+        """
+
+        self.audiofile = audiofile
+
+        self.language = language
+
+        """
+        Create folder structure
+        """
+
+        self.currentpath,\
+            self.audiopath,\
+            self.transcriptionpath,\
+            self.audiofiles = self.create_folder_structure() # create folder structure
+
+        print("loading model")
+        self.model = whisper.load_model(model)  # load model
+        print("model loaded")
+
+    def create_folder_structure(self):
+        """
+        Create folder structure for audio and transcription files
+
+        :return:  currentpath, audiopath, transcriptionpath, audiofiles
+        """
+        currentpath = os.getcwd() # get current path
+
+        if not os.path.exists(os.path.join(currentpath, 'audiofiles')):
+            print('Creating audiofiles folder')
+            os.makedirs(os.path.join(currentpath, 'audiofiles'))
+        if not os.path.exists(os.path.join(currentpath, 'transcription')):
+            print('Creating transcription folder')
+            os.makedirs(os.path.join(currentpath, 'transcription'))
+
+        audiopath = os.path.join(currentpath, 'audiofiles')  # path to audio files
+        transcriptionpath = os.path.join(currentpath, 'transcription') # path to transcription files
+
+        audiofiles = os.listdir(audiopath) # list of audio files
+
+        return currentpath, audiopath, transcriptionpath, audiofiles
+
+    def video_to_audio(self,file,  remove_video=True):
+        clip = VideoFileClip(file)
+        clip.audio.write_audiofile(os.path.join(file[:-4] + '.mp3'))
+        if remove_video:
+            os.remove(file)
+            print(f'Video {file} removed')
+        return os.path.join(file[:-4] + '.mp3')
+
+
+    def transcribe(self):
+
+        if self.audiofile is not None:
+            if self.audiofile in self.audiofiles:
+                audiofile = os.path.join(self.audiopath, self.audiofile)
+            else:
+                raise ValueError('Audio file not found')
+
+            if audiofile.endswith('.mp4'):
+                print('Converting video to audio')
+                audiofile = self.video_to_audio(audiofile)
+
+            print(f'Start transcribing Audio file: {audiofile}')
+            _stime = time()
+            result = self.model.transcribe(audiofile, verbose=True, language= self.language)
+
+            print(f'Transcription finished in {time() - _stime} seconds')
+
+            txtfilename = str(audiofile.split('/')[-1][:-4]) + '.txt'
+
+            savepath = os.path.join(self.transcriptionpath, txtfilename)
+
+            with open(savepath, 'w') as f:
+                f.write(result["text"])
+        elif self.audiofile is None or isinstance(self.audiofile, list):
+            print('No audio file specified or list of audio files')
+            print(f"{len(self.audiofiles)} audio files found in {self.audiopath}")
+            print("Start transcribing all audio files")
+            i = 0
+            for audiofile in self.audiofiles:
+
+                audiofile = os.path.join(self.audiopath, audiofile)
+
+                if audiofile.endswith('.mp4'):
+                    audiofile = self.video_to_audio(audiofile)
+
+                print(f'Start transcribing Audio file: {audiofile}')
+                _stime = time()
+                result = self.model.transcribe(audiofile, verbose=True, language=self.language)
+                print(f'Transcription finished in {time() - _stime} seconds')
+
+                txtfilename = str(audiofile.split('/')[-1][:-4]) + '.txt'
+
+                savepath = os.path.join(self.transcriptionpath, txtfilename)
+
+                with open(savepath, 'w') as f:
+                    f.write(result["text"])
+
+                i += 1
+                print(f'{i} of {len(self.audiofiles)} files transcribed')
+
+        else:
+            raise ValueError('Audio file not found')
+
+        print('Transcription finished')
+
+    def __call__(self):
+        return self.transcribe()
+    def __repr__(self):
+        return f"Transcribe(audiofile={self.audiofile}, model={self.model}, language={self.language})"
+    def __str__(self):
+        return f"Transcribe(audiofile={self.audiofile}, model={self.model}, language={self.language})"

autotranscript/version.py

@@ -0,0 +1,69 @@
+import os
+import subprocess as sp
+
+MAJOR = 1
+MINOR = 0
+MICRO = 0
+MICRO_POST = 0
+ISRELEASED = False
+VERSION = '%d.%d.%d.%d' % (MAJOR, MINOR, MICRO, MICRO_POST)
+
+# Return the git revision as a string
+# taken from numpy/numpy
+def git_version():
+    def _minimal_ext_cmd(cmd):
+        # construct minimal environment
+        env = {}
+        for k in ['SYSTEMROOT', 'PATH', 'HOME']:
+            v = os.environ.get(k)
+            if v is not None:
+                env[k] = v
+
+        # LANGUAGE is used on win32
+        env['LANGUAGE'] = 'C'
+        env['LANG'] = 'C'
+        env['LC_ALL'] = 'C'
+
+        out = sp.Popen(cmd, stdout=sp.PIPE, stderr=sp.PIPE, env=env).communicate()[0]
+        return out
+
+    try:
+        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
+        GIT_REVISION = out.strip().decode('ascii')
+    except OSError:
+        GIT_REVISION = "Unknown"
+
+    return GIT_REVISION
+
+def _get_git_version():
+    cwd = os.getcwd()
+
+    # go to the main directory
+    fdir = os.path.dirname(os.path.abspath(__file__))
+    maindir = os.path.abspath(os.path.join(fdir, ".."))
+    # maindir = fdir # os.path.join(fdir, "..")
+    os.chdir(maindir)
+
+    # get git version
+    res = git_version()
+
+    # restore the cwd
+    os.chdir(cwd)
+    return res
+
+def get_version(build_version=False):
+    if ISRELEASED:
+        return VERSION
+
+    # unreleased version
+    GIT_REVISION = _get_git_version()
+
+    if build_version:
+        import datetime as dt
+        date = dt.date.strftime(dt.datetime.now(), "%Y%m%d%H%M%S")
+        return VERSION + ".dev" + date
+    else:
+        return VERSION + ".dev0+" + GIT_REVISION[:7]
+
+
+

environment.yml

@@ -0,0 +1,96 @@
+name: whisper
+channels:
+  - pytorch
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - blas=1.0=mkl
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2022.10.11=h06a4308_0
+  - certifi=2022.9.24=py39h06a4308_0
+  - cudatoolkit=11.3.1=h9edb442_10
+  - ffmpeg=4.2.2=h20bf706_0
+  - freetype=2.12.1=h4a9f257_0
+  - giflib=5.2.1=h7b6447c_0
+  - gmp=6.2.1=h295c915_3
+  - gnutls=3.6.15=he1e5248_0
+  - intel-openmp=2021.4.0=h06a4308_3561
+  - jpeg=9e=h7f8727e_0
+  - lame=3.100=h7b6447c_0
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - lerc=3.0=h295c915_0
+  - libdeflate=1.8=h7f8727e_5
+  - libffi=3.3=he6710b0_2
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libidn2=2.3.2=h7f8727e_0
+  - libopus=1.3.1=h7b6447c_0
+  - libpng=1.6.37=hbc83047_0
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libtasn1=4.16.0=h27cfd23_0
+  - libtiff=4.4.0=hecacb30_2
+  - libunistring=0.9.10=h27cfd23_0
+  - libuv=1.40.0=h7b6447c_0
+  - libvpx=1.7.0=h439df22_0
+  - libwebp=1.2.4=h11a3e52_0
+  - libwebp-base=1.2.4=h5eee18b_0
+  - lz4-c=1.9.3=h295c915_1
+  - mkl=2021.4.0=h06a4308_640
+  - mkl-service=2.4.0=py39h7f8727e_0
+  - mkl_fft=1.3.1=py39hd3c417c_0
+  - mkl_random=1.2.2=py39h51133e4_0
+  - ncurses=6.3=h5eee18b_3
+  - nettle=3.7.3=hbbd107a_1
+  - numpy=1.23.4=py39h14f4228_0
+  - numpy-base=1.23.4=py39h31eccc5_0
+  - openh264=2.1.1=h4ff587b_0
+  - openssl=1.1.1s=h7f8727e_0
+  - pillow=9.2.0=py39hace64e9_1
+  - pip=22.2.2=py39h06a4308_0
+  - python=3.9.15=haa1d7c7_0
+  - pytorch=1.10.1=py3.9_cuda11.3_cudnn8.2.0_0
+  - pytorch-mutex=1.0=cuda
+  - readline=8.2=h5eee18b_0
+  - setuptools=65.5.0=py39h06a4308_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sqlite=3.39.3=h5082296_0
+  - tk=8.6.12=h1ccaba5_0
+  - torchaudio=0.10.1=py39_cu113
+  - torchvision=0.11.2=py39_cu113
+  - typing_extensions=4.3.0=py39h06a4308_0
+  - tzdata=2022f=h04d1e81_0
+  - wheel=0.37.1=pyhd3eb1b0_0
+  - x264=1!157.20191217=h7b6447c_0
+  - xz=5.2.6=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0
+  - zstd=1.5.2=ha4553b6_0
+  - pip:
+    - charset-normalizer==2.1.1
+    - decorator==4.4.2
+    - ffmpeg-python==0.2.0
+    - filelock==3.8.0
+    - future==0.18.2
+    - huggingface-hub==0.11.0
+    - idna==3.4
+    - imageio==2.23.0
+    - imageio-ffmpeg==0.4.7
+    - more-itertools==9.0.0
+    - moviepy==1.0.3
+    - packaging==21.3
+    - proglog==0.1.10
+    - pydub==0.25.1
+    - pyparsing==3.0.9
+    - pyyaml==6.0
+    - regex==2022.10.31
+    - requests==2.28.1
+    - semantic-version==2.10.0
+    - setuptools-rust==1.5.2
+    - tokenizers==0.13.2
+    - tqdm==4.64.1
+    - transformers==4.24.0
+    - urllib3==1.26.12
+    - whisper==1.0
+prefix: /home/jacob/anaconda3/envs/whisper

requirements.txt

@@ -0,0 +1,3 @@
+whisper~=1.0
+moviepy~=1.0.3
+setuptools~=65.5.0

setup.py

@@ -0,0 +1,38 @@
+import pkg_resources
+import os
+from setuptools import setup, find_packages
+
+module_name = "autotranscript"
+github_url = "https://github.com/Jaikinator/transcriptor"
+
+file_dir = os.path.dirname(os.path.realpath(__file__))
+absdir = lambda p: os.path.join(file_dir, p)
+
+############### versioning ###############
+verfile = os.path.abspath(os.path.join(module_name, "version.py"))
+version = {"__file__": verfile}
+
+with open(verfile, "r") as fp:
+    exec(fp.read(), version)
+
+############### setup ###############
+
+build_version = "OPTB_BUILD" in os.environ
+
+setup(
+    name=module_name,
+    version=version["get_version"](build_version),
+    packages=find_packages(),
+    python_requires="~=3.9",
+    readme="README.md",
+    install_requires = [str(r) for r in pkg_resources.parse_requirements(
+            open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
+        )
+    ],
+    url= github_url,
+    license='',
+    author='Jacob Schmieder',
+    author_email='',
+    description='Transcription tool for audio files based on Whisper',
+    #entry_points={'console_scripts': ['autotranscript = autotranscript.__main__:main']}
+)

transcribe.py

@@ -0,0 +1,4 @@
+from autotranscript import Transcribe
+
+Transcribe().transcribe()
+