add `whisper_type` arg

app.py

@@ -15,17 +15,26 @@ class App:
     def __init__(self, args):
         self.args = args
         self.app = gr.Blocks(css=CSS, theme=self.args.theme)
-        self.whisper_inf = WhisperInference() if self.args.disable_faster_whisper else FasterWhisperInference()
-        if isinstance(self.whisper_inf, FasterWhisperInference):
-            self.whisper_inf.model_dir = args.faster_whisper_model_dir
-            print("Use Faster Whisper implementation")
-        else:
-            self.whisper_inf.model_dir = args.whisper_model_dir
-            print("Use Open AI Whisper implementation")
+        self.whisper_inf = self.init_whisper()
+        print(f"Use \"{self.args.whisper_type}\" implementation")
         print(f"Device \"{self.whisper_inf.device}\" is detected")
         self.nllb_inf = NLLBInference()
         self.deepl_api = DeepLAPI()
 
+    def init_whisper(self):
+        whisper_type = self.args.whisper_type.lower().strip()
+
+        if whisper_type in ["faster_whisper", "faster-whisper"]:
+            whisper_inf = FasterWhisperInference()
+            whisper_inf.model_dir = self.args.faster_whisper_model_dir
+        if whisper_type in ["whisper"]:
+            whisper_inf = WhisperInference()
+            whisper_inf.model_dir = self.args.whisper_model_dir
+        else:
+            whisper_inf = FasterWhisperInference()
+            whisper_inf.model_dir = self.args.faster_whisper_model_dir
+        return whisper_inf
+
     @staticmethod
     def open_folder(folder_path: str):
         if os.path.exists(folder_path):
@@ -60,7 +69,7 @@ class App:
                         cb_translate = gr.Checkbox(value=False, label="Translate to English?", interactive=True)
                     with gr.Row():
                         cb_timestamp = gr.Checkbox(value=True, label="Add a timestamp to the end of the filename", interactive=True)
-                    with gr.Accordion("VAD Options", open=False, visible=not self.args.disable_faster_whisper):
+                    with gr.Accordion("VAD Options", open=False, visible=isinstance(self.whisper_inf, FasterWhisperInference)):
                         cb_vad_filter = gr.Checkbox(label="Enable Silero VAD Filter", value=False, interactive=True)
                         sd_threshold = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="Speech Threshold", value=0.5)
                         nb_min_speech_duration_ms = gr.Number(label="Minimum Speech Duration (ms)", precision=0, value=250)
@@ -134,7 +143,7 @@ class App:
                     with gr.Row():
                         cb_timestamp = gr.Checkbox(value=True, label="Add a timestamp to the end of the filename",
                                                    interactive=True)
-                    with gr.Accordion("VAD Options", open=False, visible=not self.args.disable_faster_whisper):
+                    with gr.Accordion("VAD Options", open=False, visible=isinstance(self.whisper_inf, FasterWhisperInference)):
                         cb_vad_filter = gr.Checkbox(label="Enable Silero VAD Filter", value=False, interactive=True)
                         sd_threshold = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="Speech Threshold", value=0.5)
                         nb_min_speech_duration_ms = gr.Number(label="Minimum Speech Duration (ms)", precision=0, value=250)
@@ -200,7 +209,7 @@ class App:
                         dd_file_format = gr.Dropdown(["SRT", "WebVTT", "txt"], value="SRT", label="File Format")
                     with gr.Row():
                         cb_translate = gr.Checkbox(value=False, label="Translate to English?", interactive=True)
-                    with gr.Accordion("VAD Options", open=False, visible=not self.args.disable_faster_whisper):
+                    with gr.Accordion("VAD Options", open=False, visible=isinstance(self.whisper_inf, FasterWhisperInference)):
                         cb_vad_filter = gr.Checkbox(label="Enable Silero VAD Filter", value=False, interactive=True)
                         sd_threshold = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="Speech Threshold", value=0.5)
                         nb_min_speech_duration_ms = gr.Number(label="Minimum Speech Duration (ms)", precision=0, value=250)
@@ -331,7 +340,7 @@ class App:
 
 # Create the parser for command-line arguments
 parser = argparse.ArgumentParser()
-parser.add_argument('--disable_faster_whisper', type=bool, default=False, nargs='?', const=True, help='Disable the faster_whisper implementation. faster_whipser is implemented by https://github.com/guillaumekln/faster-whisper')
+parser.add_argument('--whisper_type', type=str, default="faster-whisper", help='A type of the whisper implementation between: ["whisper", "faster-whisper"]')
 parser.add_argument('--share', type=bool, default=False, nargs='?', const=True, help='Gradio share value')
 parser.add_argument('--server_name', type=str, default=None, help='Gradio server host')
 parser.add_argument('--server_port', type=int, default=None, help='Gradio server port')

user-start-webui.bat

@@ -8,8 +8,8 @@ set USERNAME=
 set PASSWORD=
 set SHARE=
 set THEME=
-set DISABLE_FASTER_WHISPER=
 set API_OPEN=
+set WHISPER_TYPE=
 set WHISPER_MODEL_DIR=
 set FASTER_WHISPER_MODEL_DIR=
 
@@ -38,6 +38,9 @@ if /I "%DISABLE_FASTER_WHISPER%"=="true" (
 if /I "%API_OPEN%"=="true" (
     set API_OPEN=--api_open
 )
+if not "%WHISPER_TYPE%"=="" (
+    set WHISPER_TYPE_ARG=--whisper_type %WHISPER_TYPE%
+)
 if not "%WHISPER_MODEL_DIR%"=="" (
     set WHISPER_MODEL_DIR_ARG=--whisper_model_dir "%WHISPER_MODEL_DIR%"
 )
@@ -46,5 +49,5 @@ if not "%FASTER_WHISPER_MODEL_DIR%"=="" (
 )
 
 :: Call the original .bat script with optional arguments
-start-webui.bat %SERVER_NAME_ARG% %SERVER_PORT_ARG% %USERNAME_ARG% %PASSWORD_ARG% %SHARE_ARG% %THEME_ARG% %DISABLE_FASTER_WHISPER_ARG% %API_OPEN% %WHISPER_MODEL_DIR_ARG% %FASTER_WHISPER_MODEL_DIR_ARG%
+start-webui.bat %SERVER_NAME_ARG% %SERVER_PORT_ARG% %USERNAME_ARG% %PASSWORD_ARG% %SHARE_ARG% %THEME_ARG% %API_OPEN% %WHISPER_TYPE_ARG% %WHISPER_MODEL_DIR_ARG% %FASTER_WHISPER_MODEL_DIR_ARG%
 pause