store path to local audio file instead of bytes

dataset_script.py

@@ -252,7 +252,9 @@ class CommonVoice(datasets.GeneratorBasedBuilder):
                 if path in metadata:
                     result = metadata[path]
                     # set the audio feature and the path to the extracted file
+                    path = os.path.join(local_extracted_archive, path) if local_extracted_archive else path
                     result["audio"] = {"path": path, "bytes": f.read()}
-                    result["path"] = os.path.join(local_extracted_archive, path) if local_extracted_archive else None
+                    # set path to None if the audio file doesn't exist locally (i.e. in streaming mode)
+                    result["path"] = path if local_extracted_archive else None
 
                     yield path, result