clean up

handler.py

@@ -31,7 +31,6 @@ class Utterance:
         self.role = None
         self.word_count = self.get_num_words()
         self.timestamp = [starttime, endtime]
-        # self.unit_measure = endtime - starttime
         self.unit_measure = None
         self.aggregate_unit_measure = endtime
 
@@ -310,94 +309,25 @@ class EndpointHandler():
             transcript.add_utterance(Utterance(**utt))
 
         print("Running inference on %d examples..." % transcript.length())
-        # cpu_percent = psutil.cpu_percent()
         logging.set_verbosity_info()
-        # logger = logging.get_logger("transformers")
-        # logger.info(f"CPU Usage before models loaded: {cpu_percent}%")
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(
-        #     f"Used Memory before models loaded: {used_mem:.2f} GB, Total RAM: {total_mem:.2f} GB")
-
         # Uptake
         uptake_model = UptakeModel(
             self.device, self.tokenizer, self.input_builder)
         uptake_speaker = params.pop("uptake_speaker", None)
         uptake_model.run_inference(transcript, min_prev_words=params['uptake_min_num_words'],
                                    uptake_speaker=uptake_speaker)
-
-        # cpu_percent = psutil.cpu_percent()
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(
-        #     f"Used Memory after model 1 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # logger.info(f"CPU Usage after model 1 loaded: {cpu_percent}%")
-        # del uptake_model
-        # cpu_percent = psutil.cpu_percent()
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(f"Used Memory after model 1 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # logger.info(f"CPU Usage after model 1 deleted: {cpu_percent}%")
         # Reasoning
         reasoning_model = ReasoningModel(
             self.device, self.tokenizer, self.input_builder)
         reasoning_model.run_inference(transcript)
-        # cpu_percent = psutil.cpu_percent()
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(
-        #     f"Used Memory after model 2 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # logger.info(f"CPU Usage after model 2 loaded: {cpu_percent}%")
-        # # print(f"CPU Usage after model 2 loaded: {cpu_percent}%")
-        # # del reasoning_model
-        # cpu_percent = psutil.cpu_percent()
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(f"Used Memory after model 2 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # logger.info(f"CPU Usage after model 2 deleted: {cpu_percent}%")
-        # print(f"CPU Usage after model 2 deleted: {cpu_percent}%")
+
         # Question
         question_model = QuestionModel(
             self.device, self.tokenizer, self.input_builder)
         question_model.run_inference(transcript)
-        # cpu_percent = psutil.cpu_percent()
-        # logger.info(f"CPU Usage after model 3 loaded: {cpu_percent}%")
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(
-        #     f"Used Memory after model 3 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # print(f"CPU Usage after model 3 loaded: {cpu_percent}%")
-        # del question_model
-        # cpu_percent = psutil.cpu_percent()
-        # logger.info(f"CPU Usage after model 3 deleted: {cpu_percent}%")
-        # mem_info = psutil.virtual_memory()
-        # used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
-        # total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
-        # logger.info(f"Used Memory after model 3 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
-        # print(f"CPU Usage after model 3 deleted: {cpu_percent}%")
         transcript.update_utterance_roles
         talk_dist, talk_len = transcript.get_talk_distribution_and_length(uptake_speaker)
         talk_timeline = transcript.get_talk_timeline()
         word_cloud = transcript.get_word_cloud_dicts()
 
-        # return transcript.to_dict(), talk_dist, talk_len, talk_timeline, word_cloud
         return talk_dist, talk_len, talk_timeline, word_cloud
-
-# {
-#  "inputs": [
-#    {"uid": "1", "speaker": "Alice", "text": "How much is the fish?" },
-#    {"uid": "2", "speaker": "Bob", "text": "I do not know about the fish. Because you put a long side and it’s a long side. What do you think." },
-# {"uid": "3", "speaker": "Alice", "text": "OK, thank you Bob." }
-#  ],
-#  "parameters": {
-#    "uptake_min_num_words": 5,
-#    "uptake_speaker": "Bob",
-#     "filename": "sample.csv"
-#  }
-# }