Merge branch 'main' of github.com:abdeladim-s/subsai

.gitignore

@@ -130,4 +130,5 @@ dmypy.json
 
 .idea
 _docs
-assets
+assets
+.vscode

src/subsai/cli.py

@@ -124,7 +124,7 @@ def main():
                              "string)")
     parser.add_argument('-f', '--format', '--subtitles-format', default='srt',
                         help=f"Output subtitles format, available "
-                             f"formats {available_subs_formats()}")
+                             f"formats {available_subs_formats(include_extensions=False)}")
     parser.add_argument('-df', '--destination-folder', default=None,
                         help='The directory where the subtitles will be stored, default to the same folder where '
                              'the media file(s) is stored.')

src/subsai/main.py

@@ -142,11 +142,9 @@ def available_translation_languages(model: Union[str, TranslationModel]) -> list
         :return: list of available languages
         """
         if type(model) == str:
-            translation_model = Tools.create_translation_model(model)
-            langs = translation_model.available_languages()
+            langs = Tools.create_translation_model(model).available_languages()
         else:
             langs = model.available_languages()
-        del translation_model
         return langs
 
     @staticmethod

src/subsai/models/faster_whisper_model.py

@@ -200,6 +200,25 @@ class FasterWhisperModel(AbstractModel):
             'options': None,
             'default': "\"'.。,，!！?？:：”)]}、"
         },
+        'vad_filter': {
+            'type': bool,
+            'description': 'If True, use the integrated Silero VAD model to filter out parts of the audio without speech.',
+            'options': None,
+            'default': False
+        },
+        'vad_parameters': {
+            'type': dict,
+            'description': 'Parameters for splitting long audios into speech chunks using silero VAD.',
+            'options': None,
+            'default': {
+                'threshold': 0.5,
+                'min_speech_duration_ms': 250,
+                'max_speech_duration_s': float('inf'),
+                'min_silence_duration_ms': 2000,
+                'window_size_samples': 1024,
+                'speech_pad_ms': 400
+            }
+        },
     }
 
     def __init__(self, model_config):

src/subsai/utils.py

@@ -48,11 +48,20 @@ def available_translation_models() -> list:
     return models
 
 
-def available_subs_formats():
+def available_subs_formats(include_extensions=True):
     """
     Returns available subtitle formats
     from :attr:`pysubs2.FILE_EXTENSION_TO_FORMAT_IDENTIFIER`
 
+    :param include_extensions: include the dot separator in file extensions
+
     :return: list of subtitle formats
     """
-    return list(FILE_EXTENSION_TO_FORMAT_IDENTIFIER.keys())
+
+    extensions = list(FILE_EXTENSION_TO_FORMAT_IDENTIFIER.keys())
+
+    if include_extensions:
+        return extensions
+    else:
+        # remove the '.' separator from extension names
+        return [ext.split('.')[1] for ext in extensions]