Indicate utterances using utf-8. Fixes #10

Author: jordimas

e2e-tests/cmd_test.py

@@ -1,4 +1,3 @@
-import json
 import os
 import tempfile
 
@@ -7,6 +6,8 @@
 
 from faster_whisper import WhisperModel
 
+from open_dubbing.utterance import Utterance
+
 
 class TestCmd:
 
@@ -34,11 +35,9 @@ def _update_translation(self, directory):
             file.write(text)
 
     def _get_utterances(self, directory):
-        metadata_file = os.path.join(directory, "utterance_metadata_cat.json")
-        with open(metadata_file, encoding="utf-8") as json_data:
-            data = json.load(json_data)
-            utterances = data["utterances"]
-            return utterances
+        utterance = Utterance(target_language="cat", output_directory=directory)
+        utterances, _, _ = utterance.load_utterances()
+        return utterances
 
     def _assert_dubbing_action(self, directory):
         utterances = self._get_utterances(directory)

open_dubbing/utterance.py

@@ -44,7 +44,7 @@ def _get_file_name(self):
     def load_utterances(self) -> tuple[Any, PreprocessingArtifacts, Any]:
         utterance_metadata_file = self._get_file_name()
 
-        with open(utterance_metadata_file, "r") as file:
+        with open(utterance_metadata_file, "r", encoding="utf-8") as file:
             data = json.load(file)
             utterances = data["utterances"]
             preprocessing_output = PreprocessingArtifacts(