Adding improved options to resize subtitles (#1032)

buzz/db/dao/transcription_dao.py

@@ -1,3 +1,4 @@
+import uuid
 from datetime import datetime
 from uuid import UUID
 
@@ -31,7 +32,8 @@ def create_transcription(self, task: FileTranscriptionTask):
                 time_queued,
                 url,
                 whisper_model_size,
-                hugging_face_model_id
+                hugging_face_model_id,
+                word_level_timings
             ) VALUES (
                 :id,
                 :export_formats,
@@ -45,9 +47,10 @@ def create_transcription(self, task: FileTranscriptionTask):
                 :time_queued,
                 :url,
                 :whisper_model_size,
-                :hugging_face_model_id
+                :hugging_face_model_id,
+                :word_level_timings
             )
-        """
+            """
         )
         query.bindValue(":id", str(task.uid))
         query.bindValue(
@@ -82,9 +85,72 @@ def create_transcription(self, task: FileTranscriptionTask):
             if task.transcription_options.model.hugging_face_model_id
             else None,
         )
+        query.bindValue(
+            ":word_level_timings",
+            task.transcription_options.word_level_timings
+        )
+        if not query.exec():
+            raise Exception(query.lastError().text())
+
+    def copy_transcription(self, id: UUID) -> UUID:
+        query = self._create_query()
+        query.prepare("SELECT * FROM transcription WHERE id = :id")
+        query.bindValue(":id", str(id))
+        if not query.exec():
+            raise Exception(query.lastError().text())
+        if not query.next():
+            raise Exception("Transcription not found")
+
+        transcription_data = {field.name: query.value(field.name) for field in
+                              self.entity.__dataclass_fields__.values()}
+
+        new_id = uuid.uuid4()
+        transcription_data["id"] = str(new_id)
+        transcription_data["time_queued"] = datetime.now().isoformat()
+        transcription_data["status"] = FileTranscriptionTask.Status.QUEUED.value
+
+        query.prepare(
+            """
+            INSERT INTO transcription (
+                id,
+                export_formats,
+                file,
+                output_folder,
+                language,
+                model_type,
+                source,
+                status,
+                task,
+                time_queued,
+                url,
+                whisper_model_size,
+                hugging_face_model_id,
+                word_level_timings
+            ) VALUES (
+                :id,
+                :export_formats,
+                :file,
+                :output_folder,
+                :language,
+                :model_type,
+                :source,
+                :status,
+                :task,
+                :time_queued,
+                :url,
+                :whisper_model_size,
+                :hugging_face_model_id,
+                :word_level_timings
+            )
+            """
+        )
+        for key, value in transcription_data.items():
+            query.bindValue(f":{key}", value)
         if not query.exec():
             raise Exception(query.lastError().text())
 
+        return new_id
+
     def update_transcription_as_started(self, id: UUID):
         query = self._create_query()
         query.prepare(

buzz/db/entity/transcription.py

@@ -16,6 +16,7 @@ class Transcription(Entity):
     model_type: str = ModelType.WHISPER.value
     whisper_model_size: str | None = None
     hugging_face_model_id: str | None = None
+    word_level_timings: str | None = None
     language: str | None = None
     id: str = field(default_factory=lambda: str(uuid.uuid4()))
     error_message: str | None = None

buzz/db/service/transcription_service.py

@@ -19,6 +19,9 @@ def __init__(
     def create_transcription(self, task):
         self.transcription_dao.create_transcription(task)
 
+    def copy_transcription(self, id: UUID) -> UUID:
+        return self.transcription_dao.copy_transcription(id)
+
     def update_transcription_as_started(self, id: UUID):
         self.transcription_dao.update_transcription_as_started(id)
 

buzz/locale/ca_ES/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: buzz\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-11-23 22:16+0200\n"
+"POT-Creation-Date: 2024-12-28 22:29+0200\n"
 "PO-Revision-Date: 2023-02-15 05:01+0000\n"
 "Last-Translator: Jordi Mas i Hernàndez <[email protected]>\n"
 "Language-Team: Catalan <[email protected]>\n"
@@ -28,17 +28,15 @@ msgstr ""
 #: buzz/widgets/preferences_dialog/preferences_dialog.py:69
 #: buzz/widgets/preferences_dialog/models_preferences_widget.py:245
 #: buzz/widgets/transcriber/advanced_settings_dialog.py:97
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:295
-#: buzz/widgets/main_window.py:239
+#: buzz/widgets/main_window.py:244
 msgid "Ok"
 msgstr ""
 
 #: buzz/widgets/import_url_dialog.py:29
 #: buzz/widgets/preferences_dialog/preferences_dialog.py:70
 #: buzz/widgets/preferences_dialog/models_preferences_widget.py:246
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:296
 #: buzz/widgets/model_download_progress_dialog.py:29
-#: buzz/widgets/main_window.py:240
+#: buzz/widgets/main_window.py:245
 #, fuzzy
 msgid "Cancel"
 msgstr "Cancel·lat"
@@ -218,7 +216,7 @@ msgid "Download failed"
 msgstr "Baixat"
 
 #: buzz/widgets/preferences_dialog/models_preferences_widget.py:269
-#: buzz/widgets/main_window.py:296 buzz/model_loader.py:503
+#: buzz/widgets/main_window.py:301 buzz/model_loader.py:503
 msgid "Error"
 msgstr "Error"
 
@@ -321,25 +319,25 @@ msgstr ""
 msgid "Advanced..."
 msgstr ""
 
-#: buzz/widgets/main_window_toolbar.py:41
+#: buzz/widgets/main_window_toolbar.py:43
 #, fuzzy
 msgid "New File Transcription"
 msgstr "Transcripció nova"
 
-#: buzz/widgets/main_window_toolbar.py:48
+#: buzz/widgets/main_window_toolbar.py:50
 #, fuzzy
 msgid "New URL Transcription"
 msgstr "Transcripció nova"
 
-#: buzz/widgets/main_window_toolbar.py:55
+#: buzz/widgets/main_window_toolbar.py:57
 msgid "Open Transcript"
 msgstr "Obre una transcripció"
 
-#: buzz/widgets/main_window_toolbar.py:61 buzz/settings/shortcut.py:27
+#: buzz/widgets/main_window_toolbar.py:63 buzz/settings/shortcut.py:27
 msgid "Cancel Transcription"
 msgstr "Cancel·la la transcripció"
 
-#: buzz/widgets/main_window_toolbar.py:69 buzz/widgets/main_window.py:228
+#: buzz/widgets/main_window_toolbar.py:71 buzz/widgets/main_window.py:233
 #: buzz/settings/shortcut.py:26
 msgid "Clear History"
 msgstr "Neteja l'historial"
@@ -458,33 +456,54 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:156
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:158
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:172
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:180
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:182
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:90
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:279
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:281
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:280
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:282
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:297
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:72
+msgid "Resize Options"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:83
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:298
-msgid "Enter target characters per subtitle:"
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:108
+msgid "Merge Options"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:119
+msgid "Merge by gap"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:127
+msgid "Split by punctuation"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:135
+msgid "Split by max length"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:147
+msgid "Merge"
 msgstr ""
 
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
@@ -549,19 +568,19 @@ msgstr "Ajuda"
 msgid "File"
 msgstr "Fitxer"
 
-#: buzz/widgets/main_window.py:232
+#: buzz/widgets/main_window.py:237
 msgid ""
 "Are you sure you want to delete the selected transcription(s)? This action "
 "cannot be undone."
 msgstr ""
 "Esteu segur que voleu suprimir les transcripcions seleccionades? Aquesta "
 "acció no es pot desfer."
 
-#: buzz/widgets/main_window.py:260
+#: buzz/widgets/main_window.py:265
 msgid "Select audio file"
 msgstr "Selecciona un fitxer d'àudio"
 
-#: buzz/widgets/main_window.py:296
+#: buzz/widgets/main_window.py:301
 msgid "Unable to save OpenAI API key to keyring"
 msgstr ""