which is the directory of Ses01F_impro01.txt? about emotionalconversionstargan

[max-elliott]

Sorry for such a late reply, I believe the Session1\dialog\EmoEvaluation directory has the correct .txt files

[max-elliott]

@WestbrookZero do you know if this solved your issue? Thanks

[agkphysics]

I think the directory structure that comes with IEMOCAP is different to what run_preprocessing.py expects, so I had to make changes to the script get it to look in the correct places. Below are the changes I made:

diff --git a/run_preprocessing.py b/run_preprocessing.py
index cc969c2..63e49f8 100644
--- a/run_preprocessing.py
+++ b/run_preprocessing.py
@@ -30,28 +30,36 @@ def copy_files(iemocap_dir, output_dir):
     if not os.path.exists(annotations_output_dir):
         os.mkdir(annotations_output_dir)
 
-    filenames = []
-    specs = []
-    mels = []
-    labels = []
-    conts = []
-    conts_dis = []
-    speakers = []
     for session in os.listdir(iemocap_dir):
+        if not session.startswith("Session"):
+            continue
+
+        session_dir = os.path.join(iemocap_dir, session)
+
+        annotations_dir = os.path.join(session_dir, "dialog", "EmoEvaluation")
+        for filename in os.listdir(annotations_dir):
+                if not filename.endswith(".txt"):
+                    continue
+
+                src_file = os.path.join(annotations_dir, filename)
+                dest_file = os.path.join(annotations_output_dir, filename)
+                if not os.path.exists(dest_file):
+                    copyfile(src_file, dest_file)
 
-        if not session == ".DS_Store":
-            session_dir = os.path.join(iemocap_dir, session)
-            for foldername in os.listdir(session_dir):
+        wav_dir = os.path.join(session_dir, "sentences", "wav")
+        for foldername in os.listdir(wav_dir):
+            if not foldername.startswith("Ses"):
+                continue
 
-                subsession_dir = os.path.join(session_dir, foldername)
-                if not foldername == ".DS_Store":
-                    for filename in os.listdir(subsession_dir):
+            subsession_dir = os.path.join(wav_dir, foldername)
+            for filename in os.listdir(subsession_dir):
+                if not filename.endswith(".wav"):
+                    continue
 
-                        if not filename == ".DS_Store":
-                            src_file = os.path.join(subsession_dir, filename)
-                            dest_file = os.path.join(annotations_output_dir, filename) if foldername == "Annotations" else os.path.join(audio_output_dir, filename)
-                            if not os.path.exists(dest_file):
-                                copyfile(src_file, dest_file)
+                src_file = os.path.join(subsession_dir, filename)
+                dest_file = os.path.join(audio_output_dir, filename)
+                if not os.path.exists(dest_file):
+                    copyfile(src_file, dest_file)
 
         print(session + " completed.")

[max-elliott]

Yes I was aware that the version of the dataset I was using was already restructured in some way. I will look into this issue and possibly update the repo following your changes. Would you be able to create a pull request for this?

[agkphysics]

@max-elliott I've created #8 with those changes.