remove secrets

.gitignore

@@ -1 +1,2 @@
-__pycache__
+__pycache__
+.vscode

.vscode/PythonImportHelper-v2-Completion.json

@@ -487,7 +487,7 @@
         "kind": 5,
         "importPath": "main.diarization",
         "description": "main.diarization",
-        "peekOfCode": "hugging_face_token = \"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\"\npipeline = Pipeline.from_pretrained(\n    'pyannote/speaker-diarization', use_auth_token=hugging_face_token)\nuse_device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\npipeline.to(use_device)\ndef start_diarization(input_file):\n    diarization = pipeline(input_file)\n    sample_groups = []\n    speaker_groups = {}\n    for turn, _, speaker in diarization.itertracks(yield_label=True):",
+        "peekOfCode": "hugging_face_token = os.environ[\"HUGGING_FACE_TOKEN\"]\npipeline = Pipeline.from_pretrained(\n    'pyannote/speaker-diarization', use_auth_token=hugging_face_token)\nuse_device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\npipeline.to(use_device)\ndef start_diarization(input_file):\n    diarization = pipeline(input_file)\n    sample_groups = []\n    speaker_groups = {}\n    for turn, _, speaker in diarization.itertracks(yield_label=True):",
         "detail": "main.diarization",
         "documentation": {}
     },
@@ -577,7 +577,7 @@
         "kind": 5,
         "importPath": "main.summary",
         "description": "main.summary",
-        "peekOfCode": "openai.api_key = \"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\"\ndef get_summary(lang_choice: int):\n    transcribe_list = text_file_tool.read_simple_transcribe_file()\n    transcribe = \"\\n\".join(transcribe_list)\n    encoding = tiktoken.get_encoding(\"cl100k_base\")\n    token_num = len(encoding.encode(transcribe))\n    print(f\"Token number is {token_num}\")\n    language = [\"English\", \"Bahasa Indonesia\", \"Any\"]\n    result = openai.ChatCompletion.create(\n        model=\"gpt-3.5-turbo\" if token_num < 4097 else \"gpt-3.5-turbo-16k\",",
+        "peekOfCode": "openai.api_key = os.environ[\"OPEN_AI_KEY\"]\ndef get_summary(lang_choice: int):\n    transcribe_list = text_file_tool.read_simple_transcribe_file()\n    transcribe = \"\\n\".join(transcribe_list)\n    encoding = tiktoken.get_encoding(\"cl100k_base\")\n    token_num = len(encoding.encode(transcribe))\n    print(f\"Token number is {token_num}\")\n    language = [\"English\", \"Bahasa Indonesia\", \"Any\"]\n    result = openai.ChatCompletion.create(\n        model=\"gpt-3.5-turbo\" if token_num < 4097 else \"gpt-3.5-turbo-16k\",",
         "detail": "main.summary",
         "documentation": {}
     },

main/diarization.py

@@ -9,9 +9,7 @@ import os
 gc.collect()
 torch.cuda.empty_cache()
 
-# FIXME REMEMBER TO DELETE ENVIRON BEFORE COMMIT
-# hugging_face_token = os.environ["HUGGING_FACE_TOKEN"]
-hugging_face_token = "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"
+hugging_face_token = os.environ["HUGGING_FACE_TOKEN"]
 pipeline = Pipeline.from_pretrained(
     'pyannote/speaker-diarization', use_auth_token=hugging_face_token)
 use_device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

main/summary.py

@@ -1,11 +1,9 @@
 import openai
 import tiktoken
 import tool.text_file_tool as text_file_tool
+import os
 
-
-# FIXME REMEMBER TO DELETE ENVIRON BEFORE COMMIT
-# openai.api_key = os.environ["OPEN_AI_KEY"]
-openai.api_key = "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"
+openai.api_key = os.environ["OPEN_AI_KEY"]
 
 
 def get_summary(lang_choice: int):

main/transcribe.py

@@ -42,7 +42,6 @@ def start_transcribe(lang_choice: int, model_size_choice: int, progress):
             segment_txt = segment.text
             speaker_txt_list.append(segment_txt)
 
-            # TODO CHECK FOR TRIPLE QUOTES
             subtitle = f"{len(subtitle_txt_list) + 1}\n{start} --> {end}\n[{name}] {segment_txt}\n\n"
             subtitle_txt_list.append(subtitle)