Update modules/whisper/whisper_base.py

modules/whisper/whisper_base.py

@@ -296,6 +296,9 @@ class WhisperBase(ABC):
             file_count_total = 0
             process_multiple = False
             files = ""
+            
+            char_tab = "#TAB#"
+            char_newline = "#NEWLINE#"
 
             if input_multi == "Audio":
                 files = files_audio
@@ -411,36 +414,25 @@ class WhisperBase(ABC):
                 
                 # Add filename & info as first line
                 title_line = ""
-                tabbed_space = ("\t")*3
-                if file_count_total > 1 and file_count > 1: title_line += "■"
-                if add_timestamp_preview: title_line += "□"
-                if diarize_speakers: title_line += "□"
-                title_line += f'{tabbed_space}Media file:\t{info["input_source_file"]}'
-                title_line += f'\n{tabbed_space}Language:\t{info["lang"]} (probability {info["lang_prob"]}%)'
-                if params.is_translate: title_line += f'\n{tabbed_space}Translation:\t{info["transcription"]} (Handled by OpenAI Whisper)'
-                if translate_output: title_line += f'\n{tabbed_space}Translation:\t{info["translation"]} (Handled by Facebook NLLB)'
-                title_line += "■"
-
-                temp_subtitle = info["subtitle"].rstrip("\n")
-                temp_subtitle = temp_subtitle.replace("\t","□")
-                temp_subtitle = temp_subtitle.replace("\n","■")
-                total_result += title_line+temp_subtitle
-                
+                tabbed_space = char_tab*3
+                if add_timestamp_preview: title_line += char_tab
+                if diarize_speakers: title_line += char_tab
+                title_line += f'{tabbed_space}Media file:{char_tab}{info["input_source_file"]}'
+                title_line += f'{char_newline}{tabbed_space}Language:{char_tab}{info["lang"]} (probability {info["lang_prob"]}%)'
+                if params.is_translate: title_line += f'{char_newline}{tabbed_space}Translation:{char_tab}{info["transcription"]} (Handled by OpenAI Whisper)'
+                if translate_output: title_line += f'{char_newline}{tabbed_space}Translation:{char_tab}{info["translation"]} (Handled by Facebook NLLB)'
+                title_line += char_newline
+
+                total_result += title_line+info["subtitle"]
                 total_time += info["time_for_task"]
             
             time_end = datetime.now()
+            total_info = f"Processed {file_count} {'file' if file_count == 1 else 'files'} in {self.format_time((time_end-time_start).total_seconds())}"
             #total_info += f"Total processing time:\t{self.format_time((time_end-time_start).total_seconds())}"
-
-            total_info = ""
-            if params.is_translate or translate_output:
-                total_info = "Translation:\tEnabled"
-            if diarize_speakers:
-                if total_info != "": total_info += "\n"
-                total_info += "Diarization:\tEnabled"
-            if total_info != "": total_info += "\n\n"
-            total_info += f"Processed {file_count} {'file' if file_count == 1 else 'files'} in {self.format_time((time_end-time_start).total_seconds())}"
-
-            result_str = self.transform_text_to_list(total_result,"□","■") #Transform to gr.Dataframe format
+            
+            result_str = self.transform_text_to_list(total_result) #Transform to gr.Dataframe format
+            result_str = result_str.replace(char_tab,"\t")
+            result_str = result_str.replace(char_newline,"\n")
             result_file_path = [info['path'] for info in files_to_download.values()]
 
             return [result_str,result_file_path,total_info]
@@ -636,12 +628,12 @@ class WhisperBase(ABC):
         gc.collect()
 
     @staticmethod
-    def transform_text_to_list(inputdata: str,char_tab: str, char_newline: str) -> list:
+    def transform_text_to_list(inputdata: str) -> list:
         outputdata = []
-        temp_inputdata = (inputdata.strip("\n")).split(char_newline)
+        temp_inputdata = inputdata.strip.split("\n")
         for temp_line in temp_inputdata:
             temp_line_list = []	
-            temp_line_items = temp_line.split(char_tab)
+            temp_line_items = temp_line.split("\t")
             for temp_line_item in temp_line_items:
                 temp_line_list.append(temp_line_item)	
             outputdata.append(temp_line_list)