Argument Refactoring and Web Server Argument

* Updated Arguments for valid languages * Added port argument and detection. Web server will start if `portnumber` arg is added * Web server will die peacefully rather forcefully * Transcription will save when app is killed using `ctrl` + `c`
cyberofficial · Aug 7, 2023 · f61b71a · f61b71a
1 parent 07ec714
commit f61b71a
Show file tree

Hide file tree

Showing 4 changed files with 59 additions and 27 deletions.
diff --git a/modules/api_backend.py b/modules/api_backend.py
@@ -2,7 +2,7 @@
 from flask import Flask, send_from_directory, url_for
 from threading import Thread
 
-def flask_server(operation, port):
+def flask_server(operation, portnumber):
     if operation == "start":
         # Define paths
         script_dir = os.path.dirname(os.path.realpath(__file__))
@@ -15,7 +15,7 @@ def flask_server(operation, port):
         app.config["DEBUG"] = False
 
         # Set port number
-        port = 5000
+        port = portnumber
 
         # Time to start the server
         print("Starting Flask Server on port:", port)
@@ -52,4 +52,10 @@ def run():
                 app.do_teardown_appcontext()
 
         # Start the server in a new thread
-        Thread(target=run).start()
+        Thread(target=run).start()
+
+def kill_server():
+    print("Killing Server")
+    os._exit(0)
+
+print("Web Server Module Loaded")
diff --git a/modules/checkenv.py b/modules/checkenv.py
@@ -39,4 +39,5 @@ def env_message():
 elif current_os == 'linux':
     os.system('clear')
 
+print("Check ENV Module Loaded")
 print("Checking if you are in a virtual environment...\n\n")
diff --git a/modules/parser_args.py b/modules/parser_args.py
@@ -1,4 +1,14 @@
 from modules.imports import *
+from modules.languages import get_valid_languages
+
+# Define a constant variable for valid language choices
+VALID_LANGUAGES = get_valid_languages()
+
+def valid_port_number(value):
+    port = int(value)
+    if not 1 <= port <= 65535:
+        raise argparse.ArgumentTypeError(f"Invalid port number: {value}. Please choose a number between 1 and 65535.")
+    return port
 
 def set_model_by_ram(ram, language):
     ram = ram.lower()
@@ -40,10 +50,8 @@ def parse_arguments():
     parser.add_argument("--no_log", action='store_true', help="Only show the last line of the transcription.")
     parser.add_argument("--translate", action='store_true', help="Translate the transcriptions to English.")
     parser.add_argument("--transcribe", action='store_true', help="transcribe the text into the desired language.")
-    parser.add_argument("--language", help="Language to translate from.", type=str,
-                        choices=["af", "am", "ar", "as", "az", "ba", "be", "bg", "bn", "bo", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fo", "fr", "gl", "gu", "ha", "haw", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jw", "ka", "kk", "km", "kn", "ko", "la", "lb", "ln", "lo", "lt", "lv", "mg", "mi", "mk", "ml", "mn", "mr", "ms", "mt", "my", "ne", "nl", "nn", "no", "oc", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "sn", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "tg", "th", "tk", "tl", "tr", "tt", "uk", "ur", "uz", "vi", "yi", "yo", "zh", "Afrikaans", "Albanian", "Amharic", "Arabic", "Armenian", "Assamese", "Azerbaijani", "Bashkir", "Basque", "Belarusian", "Bengali", "Bosnian", "Breton", "Bulgarian", "Burmese", "Castilian", "Catalan", "Chinese", "Croatian", "Czech", "Danish", "Dutch", "English", "Estonian", "Faroese", "Finnish", "Flemish", "French", "Galician", "Georgian", "German", "Greek", "Gujarati", "Haitian", "Haitian Creole", "Hausa", "Hawaiian", "Hebrew", "Hindi", "Hungarian", "Icelandic", "Indonesian", "Italian", "Japanese", "Javanese", "Kannada", "Kazakh", "Khmer", "Korean", "Lao", "Latin", "Latvian", "Letzeburgesch", "Lingala", "Lithuanian", "Luxembourgish", "Macedonian", "Malagasy", "Malay", "Malayalam", "Maltese", "Maori", "Marathi", "Moldavian", "Moldovan", "Mongolian", "Myanmar", "Nepali", "Norwegian", "Nynorsk", "Occitan", "Panjabi", "Pashto", "Persian", "Polish", "Portuguese", "Punjabi", "Pushto", "Romanian", "Russian", "Sanskrit", "Serbian", "Shona", "Sindhi", "Sinhala", "Sinhalese", "Slovak", "Slovenian", "Somali", "Spanish", "Sundanese", "Swahili", "Swedish", "Tagalog", "Tajik", "Tamil", "Tatar", "Telugu", "Thai", "Tibetan", "Turkish", "Turkmen", "Ukrainian", "Urdu", "Uzbek", "Valencian", "Vietnamese", "Welsh", "Yiddish", "Yoruba"])
-    parser.add_argument("--target_language", help="Language to translate to.", type=str,
-                        choices=["af", "am", "ar", "as", "az", "ba", "be", "bg", "bn", "bo", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fo", "fr", "gl", "gu", "ha", "haw", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jw", "ka", "kk", "km", "kn", "ko", "la", "lb", "ln", "lo", "lt", "lv", "mg", "mi", "mk", "ml", "mn", "mr", "ms", "mt", "my", "ne", "nl", "nn", "no", "oc", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "sn", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "tg", "th", "tk", "tl", "tr", "tt", "uk", "ur", "uz", "vi", "yi", "yo", "zh", "Afrikaans", "Albanian", "Amharic", "Arabic", "Armenian", "Assamese", "Azerbaijani", "Bashkir", "Basque", "Belarusian", "Bengali", "Bosnian", "Breton", "Bulgarian", "Burmese", "Castilian", "Catalan", "Chinese", "Croatian", "Czech", "Danish", "Dutch", "English", "Estonian", "Faroese", "Finnish", "Flemish", "French", "Galician", "Georgian", "German", "Greek", "Gujarati", "Haitian", "Haitian Creole", "Hausa", "Hawaiian", "Hebrew", "Hindi", "Hungarian", "Icelandic", "Indonesian", "Italian", "Japanese", "Javanese", "Kannada", "Kazakh", "Khmer", "Korean", "Lao", "Latin", "Latvian", "Letzeburgesch", "Lingala", "Lithuanian", "Luxembourgish", "Macedonian", "Malagasy", "Malay", "Malayalam", "Maltese", "Maori", "Marathi", "Moldavian", "Moldovan", "Mongolian", "Myanmar", "Nepali", "Norwegian", "Nynorsk", "Occitan", "Panjabi", "Pashto", "Persian", "Polish", "Portuguese", "Punjabi", "Pushto", "Romanian", "Russian", "Sanskrit", "Serbian", "Shona", "Sindhi", "Sinhala", "Sinhalese", "Slovak", "Slovenian", "Somali", "Spanish", "Sundanese", "Swahili", "Swedish", "Tagalog", "Tajik", "Tamil", "Tatar", "Telugu", "Thai", "Tibetan", "Turkish", "Turkmen", "Ukrainian", "Urdu", "Uzbek", "Valencian", "Vietnamese", "Welsh", "Yiddish", "Yoruba"])
+    parser.add_argument("--language", help="Language to translate from.", type=str, choices=VALID_LANGUAGES)
+    parser.add_argument("--target_language", help="Language to translate to.", type=str, choices=VALID_LANGUAGES)
     parser.add_argument("--auto_model_swap", action='store_true', help="Automatically swap model based on detected language.")
     parser.add_argument("--device", default="cuda", help="Device to use for model. If not specified, will use CUDA if available. Available options: cpu, cuda")
     parser.add_argument("--cuda_device", default=0, help="CUDA device to use for model. If not specified, will use CUDA device 0.", type=int)
@@ -55,6 +63,9 @@ def parse_arguments():
     parser.add_argument("--use_finetune", action='store_true', help="Use finetuned model.")
     parser.add_argument("--updatebranch", default="master", help="Check which branch from the repo to check for updates. Default is master, choices are master and dev-testing and bleeding-under-work. To turn off update checks use disable. bleeding-under-work is basically latest changes and can break at any time.", choices=["master", "dev-testing", "disable", "bleeding-under-work"])
     parser.add_argument("--keep_temp", action='store_true', help="Keep temporary audio files.")
+    # add portnumber argument, but make it optional, so if a portnumber is set we know to run the webserver if there is no portnumber we don't run the webserver, though make the choices 0-65535
+    parser.add_argument(
+    "--portnumber", default=None, help="Port number to run the web server on. If not specified, the web server will not run.", type=valid_port_number)
     parser.add_argument("--about", action='store_true', help="About the project.")
     args = parser.parse_args()
     return args

diff --git a/transcribe_audio.py b/transcribe_audio.py
@@ -2,13 +2,18 @@
 isinenv = checkenv.in_virtualenv()
 
 if isinenv == False:
-    checkenv.env_message()
+    print("Checking if portable version is being used...")
+    if os.path.exists("transcribe_audio.exe"):
+        print("Portable version detected, continuing with script...\n\n")
+    else:
+        checkenv.env_message()
 else:
     print("You are in a virtual environment, continuing with script...\n\n")
 
 try:
     print("Loading Primary Imports")
     from modules.imports import *
+    print("\n\n")
 except Exception as e:
     print("Error Loading Primary Imports")
     print("Check the Modules folder for the imports.py file and make sure it is not missing or corrupted.")
@@ -17,8 +22,6 @@
 
 init()
 
-api_backend.flask_server(operation="start", portnumber=5000)
-
 try:
     cuda_available = torch.cuda.is_available()
 except:
@@ -29,6 +32,10 @@
 def main():
     args = parser_args.parse_arguments()
 
+    if args.portnumber:
+        print("Port number was set, so spinning up a web server...")
+        api_backend.flask_server(operation="start", portnumber=args.portnumber)
+
     # if args.updatebranch is set as disable then skip
     if args.updatebranch != "disable":
         print("\nChecking for updates...")
@@ -561,24 +568,31 @@ def is_input_device(device_index):
             print("Exiting...")
             if args.discord_webhook:
                 send_to_discord_webhook(webhook_url, "Service has stopped.")
-            break
+            # break
+
+            if not os.path.isdir('out'):
+                os.mkdir('out')
+
+            transcript = os.path.join(os.getcwd(), 'out', 'transcription.txt')
+            if os.path.isfile(transcript):
+                transcript = os.path.join(os.getcwd(), 'out', 'transcription_' + str(len(os.listdir('out'))) + '.txt')
+            transcription_file = open(transcript, 'w',  encoding='utf-8')
+
+            for original_text, translated_text, transcribed_text, detected_language in transcription:
+                transcription_file.write(f"-=-=-=-=-=-=-=-\nOriginal ({detected_language}): {original_text}\n")
+                if translated_text:
+                    transcription_file.write(f"Translation: {translated_text}\n")
+                if transcribed_text:
+                    transcription_file.write(f"Transcription: {transcribed_text}\n")
+            transcription_file.close()
+            print(f"Transcription was saved to {transcript}")
+
+            if args.portnumber:
+                api_backend.kill_server()
+
+            sys.exit(0)
+
 
-    if not os.path.isdir('out'):
-        os.mkdir('out')
-
-    transcript = os.path.join(os.getcwd(), 'out', 'transcription.txt')
-    if os.path.isfile(transcript):
-        transcript = os.path.join(os.getcwd(), 'out', 'transcription_' + str(len(os.listdir('out'))) + '.txt')
-    transcription_file = open(transcript, 'w',  encoding='utf-8')
-
-    for original_text, translated_text, transcribed_text, detected_language in transcription:
-        transcription_file.write(f"-=-=-=-=-=-=-=-\nOriginal ({detected_language}): {original_text}\n")
-        if translated_text:
-            transcription_file.write(f"Translation: {translated_text}\n")
-        if transcribed_text:
-            transcription_file.write(f"Transcription: {transcribed_text}\n")
-    transcription_file.close()
-    print(f"Transcription was saved to {transcript}")
 
 
 if __name__ == "__main__":