Add logging infrastructure (#42)

.gitignore

@@ -3,4 +3,5 @@ __pycache__/
 .venv/
 venv
 output
-tiny.pt
+tiny.pt
+Transcribe.log

AudioRecorder.py

@@ -1,14 +1,18 @@
 import custom_speech_recognition as sr
 import pyaudiowpatch as pyaudio
 from datetime import datetime
+import app_logging as al
 
 RECORD_TIMEOUT = 3
 ENERGY_THRESHOLD = 1000
 DYNAMIC_ENERGY_THRESHOLD = False
 
+root_logger = al.get_logger()
+
 
 class BaseRecorder:
  def __init__(self, source, source_name):
+ root_logger.info(BaseRecorder.__name__)
  self.recorder = sr.Recognizer()
  self.recorder.energy_threshold = ENERGY_THRESHOLD
  self.recorder.dynamic_energy_threshold = DYNAMIC_ENERGY_THRESHOLD
@@ -20,6 +24,7 @@ def __init__(self, source, source_name):
  self.source_name = source_name
 
  def adjust_for_noise(self, device_name, msg):
+ root_logger.info(BaseRecorder.adjust_for_noise.__name__)
  print(f"[INFO] Adjusting for ambient noise from {device_name}. " + msg)
  with self.source:
  self.recorder.adjust_for_ambient_noise(self.source)
@@ -36,12 +41,14 @@ def record_callback(_, audio: sr.AudioData) -> None:
 
 class DefaultMicRecorder(BaseRecorder):
  def __init__(self):
+ root_logger.info(DefaultMicRecorder.__name__)
  super().__init__(source=sr.Microphone(sample_rate=16000), source_name="You")
  self.adjust_for_noise("Default Mic", "Please make some noise from the Default Mic...")
 
 
 class DefaultSpeakerRecorder(BaseRecorder):
  def __init__(self):
+ root_logger.info(DefaultSpeakerRecorder.__name__)
  with pyaudio.PyAudio() as p:
  wasapi_info = p.get_host_api_info_by_type(pyaudio.paWASAPI)
  default_speakers = p.get_device_info_by_index(wasapi_info["defaultOutputDevice"])

AudioTranscriber.py

@@ -10,6 +10,7 @@
 from heapq import merge
 import conversation
 
+
 PHRASE_TIMEOUT = 3.05
 
 

GPTResponder.py

@@ -6,13 +6,17 @@
 import conversation
 import constants
 import configuration
+import app_logging as al
+
 
 # Number of phrases to use for generating a response
 MAX_PHRASES = 20
+root_logger = al.get_logger()
 
 
 class GPTResponder:
  def __init__(self, convo: conversation.Conversation):
+ root_logger.info(GPTResponder.__name__)
  self.response = prompts.INITIAL_RESPONSE
  self.response_interval = 2
  self.gl_vars = GlobalVars.TranscriptionGlobals()
@@ -80,4 +84,5 @@ def respond_to_transcriber(self, transcriber):
  time.sleep(0.3)
 
  def update_response_interval(self, interval):
+ root_logger.info(GPTResponder.update_response_interval.__name__)
  self.response_interval = interval

GlobalVars.py

@@ -3,8 +3,11 @@
 import AudioRecorder
 import customtkinter as ctk
 import Singleton
+import app_logging as al
 
 
+root_logger = al.get_logger()
+
 class TranscriptionGlobals(Singleton.Singleton):
  """Global constants for audio processing. It is implemented as a Singleton class.
  """
@@ -22,6 +25,7 @@ class TranscriptionGlobals(Singleton.Singleton):
  api_key: str = None
 
  def __init__(self, key: str = 'API_KEY'):
+ root_logger.info(TranscriptionGlobals.__name__)
  if self.audio_queue is None:
  self.audio_queue = queue.Queue()
  if self.user_audio_recorder is None:

app_logging.py

@@ -0,0 +1,26 @@
+import queue
+import logging
+from logging import handlers
+import constants
+
+
+root_logger: logging.Logger = logging.getLogger(name=constants.LOG_NAME)
+
+
+def initiate_log(config: dict) -> handlers.QueueListener:
+ # Initiate logging
+ que = queue.Queue(-1)
+ queue_handler = handlers.QueueHandler(que)
+ handler = logging.FileHandler(config['General']['log_file'], mode='w', encoding='utf-8')
+ log_listener = handlers.QueueListener(que, handler)
+ root_logger.setLevel(level=logging.INFO)
+ root_logger.addHandler(queue_handler)
+ log_formatter = logging.Formatter('%(asctime)s %(levelname)s %(threadName)s: %(message)s')
+ handler.setFormatter(log_formatter)
+ log_listener.start()
+ root_logger.info('Logging started for application!')
+ return log_listener
+
+
+def get_logger() -> logging.Logger:
+ return root_logger

constants.py

@@ -1,7 +1,9 @@
 """Globally used constants
 """
 
-PERSONA_YOU = "You"
-PERSONA_ASSISTANT = "Assistant"
-PERSONA_SYSTEM = "System"
-PERSONA_SPEAKER = "Speaker"
+PERSONA_YOU = 'You'
+PERSONA_ASSISTANT = 'Assistant'
+PERSONA_SYSTEM = 'System'
+PERSONA_SPEAKER = 'Speaker'
+
+LOG_NAME = 'Transcribe'

interactions.py

@@ -1,9 +1,14 @@
 import subprocess
 import socket
+import app_logging as al
+
+
+root_logger = al.get_logger()
 
 
 def create_params() -> dict:
  try:
+ root_logger.info(create_params.__name__)
  git_version = subprocess.check_output(
  ['git', 'rev-parse', '--short', 'HEAD']).decode("utf-8").strip()
  except subprocess.CalledProcessError as process_exception:

main.py

@@ -11,10 +11,11 @@
 import TranscriberModels
 import interactions
 import ui
-from language import LANGUAGES_DICT
 import GlobalVars
 import configuration
 import conversation
+import app_logging
+
 
 def main():
  # Set up all arguments
@@ -47,10 +48,23 @@ def main():
  line argument. Behavior is undefined.')
  args = cmd_args.parse_args()
 
+ # Initiate config
+ config = configuration.Config().get_data()
+
+ # Initiate global variables
+ # Two calls to GlobalVars.TranscriptionGlobals is on purpose
+ global_vars = GlobalVars.TranscriptionGlobals()
+
+ global_vars = GlobalVars.TranscriptionGlobals(key=config["OpenAI"]["api_key"])
+
+ # Initiate logging
+ log_listener = app_logging.initiate_log(config=config)
+
  try:
  subprocess.run(["ffmpeg", "-version"],
- stdout = subprocess.DEVNULL,
- stderr = subprocess.DEVNULL)
+ stdout=subprocess.DEVNULL,
+ stderr=subprocess.DEVNULL,
+ check=True)
  except FileNotFoundError:
  print("ERROR: The ffmpeg library is not installed. Please install \
  ffmpeg and try again.")
@@ -64,13 +78,6 @@ def main():
  except ConnectionError:
  print('[INFO] Operating in Desktop mode')
 
- config = configuration.Config().get_data()
-
- # Two calls to GlobalVars.TranscriptionGlobals is on purpose
- global_vars = GlobalVars.TranscriptionGlobals()
-
- global_vars = GlobalVars.TranscriptionGlobals(key=config["OpenAI"]["api_key"])
-
  # Command line arg for api_key takes preference over api_key specified in parameters.yaml file
  if args.api_key is not None:
  api_key = args.api_key
@@ -104,13 +111,15 @@ def main():
  model,
  convo=convo)
  transcribe_thread = threading.Thread(target=global_vars.transcriber.transcribe_audio_queue,
+ name='Transcribe',
  args=(global_vars.audio_queue,))
  transcribe_thread.daemon = True
  transcribe_thread.start()
 
  global_vars.responder = GPTResponder(convo=convo)
 
  respond_thread = threading.Thread(target=global_vars.responder.respond_to_transcriber,
+ name='Respond',
  args=(global_vars.transcriber,))
  respond_thread.daemon = True
  respond_thread.start()
@@ -136,6 +145,7 @@ def main():
  update_interval_slider, global_vars.freeze_state)
 
  root.mainloop()
+ log_listener.stop()
 
 
 if __name__ == "__main__":

parameters.yaml

@@ -9,3 +9,6 @@ OpenAI:
 # See this link for available models
 # https://platform.openai.com/docs/models/continuous-model-upgrades
  ai_model: gpt-3.5-turbo-0301
+
+General:
+ log_file: 'Transcribe.log'

ui.py

@@ -7,7 +7,10 @@
 import customtkinter as ctk
 import GlobalVars
 import GPTResponder
+import app_logging as al
 
+
+root_logger = al.get_logger()
 UI_FONT_SIZE = 20
 
 
@@ -21,23 +24,27 @@ def __init__(self):
  def copy_to_clipboard(self):
  """Copy transcription text data to clipboard
  """
+ root_logger.info(ui_callbacks.copy_to_clipboard.__name__)
  pyperclip.copy(self.global_vars.transcriber.get_transcript())
 
  def save_file(self):
  """Save transcription text data to file
  """
+ root_logger.info(ui_callbacks.save_file.__name__)
  filename = ctk.filedialog.asksaveasfilename()
  with open(file=filename, mode="w", encoding='utf-8') as file_handle:
  file_handle.write(self.global_vars.transcriber.get_transcript())
 
  def freeze_unfreeze(self):
  """Respond to start / stop of seeking responses from openAI API"""
+ root_logger.info(ui_callbacks.freeze_unfreeze.__name__)
  self.global_vars.freeze_state[0] = not self.global_vars.freeze_state[0] # Invert the state
  self.global_vars.freeze_button.configure(
  text="Suggest Response" if self.global_vars.freeze_state[0] else "Do Not Suggest Response"
  )
 
  def set_transcript_state(self):
+ root_logger.info(ui_callbacks.set_transcript_state.__name__)
  self.global_vars.transcriber.transcribe = not self.global_vars.transcriber.transcribe
  self.global_vars.transcript_button.configure(
  text="Pause Transcript" if self.global_vars.transcriber.transcribe else "Start Transcript"
@@ -99,12 +106,14 @@ def clear_transcriber_context(transcriber: AudioTranscriber,
  textbox: textbox to be updated
  text: updated text
  """
+ root_logger.info(clear_transcriber_context.__name__)
  transcriber.clear_transcript_data()
  with audio_queue.mutex:
  audio_queue.queue.clear()
 
 
 def create_ui_components(root):
+ root_logger.info(create_ui_components.__name__)
  ctk.set_appearance_mode("dark")
  ctk.set_default_color_theme("dark-blue")
  root.title("Transcribe")