Refactoring: saving transcripts

save in data folder and refactor save_transcript to be part of FileManager class

README.md

@@ -56,13 +56,17 @@ Jobs specify tasks for transcript creation. A job contains the following informa
 
 ## to-do
 
-### Feature: specific model
+### Feature request: specific model
 
 add an opitonal model path to the json config
 - `model_path`:Optional[string]: The path to a specific language model to be used (mainly for testing)
 
+### Refactoring: saving transcripts
+
+let the generate transcript return a transcript object that is the saved by file manager
+give file manager an init to specify the saving folder
+
 ### Other
-- seperate data production form code
 - remember to accept the conditions on models if you use huggingface
 - check warnings
 - downloader for tib-av

src/file_manager.py

@@ -1,5 +1,6 @@
 import logging
 import os
+import json
 
 from pydub import AudioSegment
 from pytube import YouTube, exceptions as pytube_exceptions
@@ -12,8 +13,8 @@ class FileManager:
     FileManager class that handles operations such as downloading and converting audio.
     """
 
-    def __init__(self):
+    def __init__(self, folder: str="data/results"):
-        pass
+        self.folder = folder
 
     @staticmethod
     def download_youtube_audio(youtube_link: str, filename: str):
@@ -77,3 +78,26 @@ class FileManager:
         else:
             logging.error(f"Unsupported file format: {ext}.")
             raise ValueError("Unsupported file format.")
+
+    def save_transcript(self, transcript_data: dict, output_json_file: str, output_txt_file: str):
+        """
+        Save the transcription result to a json file and a text file.
+        :param transcript_data: dict: Transcription data.
+        :param output_json_file: str: Name for the output json file.
+        :param output_txt_file: str: Name for the output text file.
+        """
+        output_json_file = os.path.join(self.folder, output_json_file)
+        output_txt_file = os.path.join(self.folder, output_txt_file)
+
+        try:
+            # Save full results to a json file
+            with open(output_json_file, "w") as f:
+                json.dump(transcript_data, f)
+
+            # Save just the transcripts to a .txt file
+            transcripts = [seg["text"] for seg in transcript_data["segments"]]
+            with open(output_txt_file, "w") as f:
+                f.write("\n".join(transcripts))
+        except Exception as e:
+            logger.exception("Failed to save transcript: %s", e)
+            raise

src/transcriber.py

@@ -1,5 +1,4 @@
 import gc
-import json
 import logging
 import os
 
@@ -83,25 +82,6 @@ class Transcriber:
             logger.exception("Failed to transcribe: %s", e)
             raise
 
-    def save_transcript(self, output_json_file: str, output_txt_file: str):
-        """
-        Save the transcription result to a json file and a text file.
-        :param output_json_file: str: Path to the output json file.
-        :param output_txt_file: str: Path to the output text file.
-        """
-        try:
-            # Save full results to a json file
-            with open(output_json_file, "w") as f:
-                json.dump(self.transcript_output, f)
-
-            # Save just the transcripts to a .txt file
-            transcripts = [seg["text"] for seg in self.transcript_output["segments"]]
-            with open(output_txt_file, "w") as f:
-                f.write("\n".join(transcripts))
-        except Exception as e:
-            logger.exception("Failed to save transcript: %s", e)
-            raise
-
     @staticmethod
     def _clear_memory():
         """

src/transcript_generator.py

@@ -36,10 +36,10 @@ class TranscriptGenerator:
                     self.file_manager.convert_to_wav(mp4_filename, wav_filename)
                 else:
                     wav_filename = self.file_manager.load_local_file(source)
-                self.transcriber.transcribe(wav_filename)
+                transcript_data = self.transcriber.transcribe(wav_filename)
                 json_output_file = f"result_{self.job_name}_{i + 1}.json"
                 txt_output_file = f"transcripts_{self.job_name}_{i + 1}.txt"
-                self.transcriber.save_transcript(json_output_file, txt_output_file)
+                self.file_manager.save_transcript(transcript_data, json_output_file, txt_output_file)
             except Exception as e:
                 logger.exception(
                     f"Failed to generate transcript for source {source}. Error: {str(e)}"