first 'working' version

transcription/job_utils.py

@@ -190,6 +190,9 @@ def get_progress(job_name: str, config: dict) -> int:
     input_dir = os.path.join(config['jobs']['root_directory'], job_name, chunk_input_subdir)
     output_dir = os.path.join(config['jobs']['root_directory'], job_name, chunk_output_subdir)
 
+    if not os.path.exists(input_dir) or not os.path.exists(output_dir):
+        return 0
+
     num_input_files = len(os.listdir(input_dir))
     num_output_files = len(os.listdir(output_dir))
 

transcription/transcription_helper.py

@@ -3,11 +3,11 @@ import os
 from multiprocessing import Lock
 from concurrent.futures import ProcessPoolExecutor
 
-import job_utils
 from utils import get_logger
-from audio_processing import split_audio, convert_to_wav
-from job_utils import is_job, remove_job, create_job, get_processing, set_processing
-from transcription import transcribe_audio
+from transcription import job_utils
+from transcription.job_utils import is_job, remove_job, create_job, get_processing, set_processing
+from transcription.audio_processing import split_audio, convert_to_wav
+from transcription.transcription import transcribe_audio
 
 job_update_lock = Lock()
 default_input_audio_file_name = 'input_audio'
@@ -36,7 +36,7 @@ def transcribe(audio_file_path: str,
     job_name = os.path.basename(audio_file_path).split('.')[0]
     job_dir = os.path.join(config['jobs']['root_directory'], job_name)
 
-    logger.info(f"Transcribing {audio_file_path} to {job_dir}")
+    logger.info(f"Transcribing {audio_file_path} to {job_dir}, blocking={blocking}, overwrite={overwrite}")
 
     # check, if a job with the same audio file already exists
     job_already_exists = is_job(job_name, config)
@@ -129,7 +129,7 @@ def run_transcription_job(job_name: str,
         logger.info(f'Combining output text chunks for job {job_name}')
         output_chunk_folder = os.path.join(config['jobs']['root_directory'], job_name, job_utils.chunk_output_subdir)
         output_text = ''
-        for text_chunk_file in sorted(os.listdir(output_chunk_folder)):
+        for text_chunk_file in sorted(os.listdir(output_chunk_folder), key=lambda x: int(x.split('_')[1].split('.')[0])):
             with open(os.path.join(output_chunk_folder, text_chunk_file), 'r') as text_chunk:
                 output_text += text_chunk.read() + ' '
 

transcription/utils.py

@@ -1,32 +0,0 @@
-import sys
-import logging
-from logging import Logger
-
-
-def get_logger(name: str) -> Logger:
-    """
-    Get a logger instance.
-    :param name: name of the logger
-    :return: logger instance
-    """
-    logger = logging.getLogger(name)
-    logger.setLevel(logging.INFO)
-
-    # create a file handler
-    file_handler = logging.FileHandler(f'{name}.log')
-    file_handler.setLevel(logging.INFO)
-
-    # create stdout handler
-    stdout_handler = logging.StreamHandler(sys.stdout)
-    stdout_handler.setLevel(logging.INFO)
-
-    # create a logging format
-    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-    file_handler.setFormatter(formatter)
-    stdout_handler.setFormatter(formatter)
-
-    # add the handlers to the logger
-    logger.addHandler(file_handler)
-    logger.addHandler(stdout_handler)
-
-    return logger