fix line too long

espnet · ftshijt · Jan 2, 2025 · Nov 30, 2024 · Dec 12, 2024 · Dec 12, 2024
commit bee1b67beae69a56a44403307d921024bd3e7883
diff --git a/egs2/edacc/asr1/local/data_prep.py b/egs2/edacc/asr1/local/data_prep.py
@@ -24,7 +24,10 @@ def generate_data_files(
         segments = os.path.join(edacc_root, x, "segments")
         utt2spk = os.path.join(edacc_root, x, "utt2spk")
 
-        os.makedirs(os.path.join(target_root, x), exist_ok=True)
+        os.makedirs(
+            os.path.join(target_root, x),
+            exist_ok=True,
+        )
 
         # process utt2spk
         utter_spk_map = {}
@@ -41,7 +44,9 @@ def generate_data_files(
                         elif "C30" in utter and int(utter[-9:]) < 387:
                             utter = utter.replace("C30", "C30_P1")
                         utter_spk_map[utter] = spk
-                        utt2spk_out.write(f"{utter_spk_map[utter]}-{utter} {spk}\n")
+                        utt2spk_out.write(
+                            f"{utter_spk_map[utter]}-{utter} {spk}\n"
+                        )
                         utt_list.append(utter)
 
         if x == "dev":
@@ -66,22 +71,32 @@ def generate_data_files(
             if os.path.exists(text):
                 with open(text, "r") as text:
                     for line in text:
-                        utter, txt = line.strip().split(maxsplit=1)
+                        (
+                            utter,
+                            txt,
+                        ) = line.strip().split(maxsplit=1)
                         # process utter for C30
                         if "C30" in utter and int(utter[-9:]) >= 387:
                             new_number = int(utter[-9:]) - 387
                             utter = "EDACC-C30_P2-" + f"{new_number:09d}"
                         elif "C30" in utter and int(utter[-9:]) < 387:
                             utter = utter.replace("C30", "C30_P1")
-                        text_out.write(f"{utter_spk_map[utter]}-{utter} {txt}\n")
+                        text_out.write(
+                            f"{utter_spk_map[utter]}-{utter} {txt}\n"
+                        )
 
         # process segments and wav.scp
         wavID_set = set()
         with open(seg_out, "w") as seg_out, open(scp_out, "w") as scp_out:
             if os.path.exists(segments):
                 with open(segments, "r") as segments:
                     for line in segments:
-                        utter, wavID, start, end = line.strip().split()
+                        (
+                            utter,
+                            wavID,
+                            start,
+                            end,
+                        ) = line.strip().split()
                         # process utter for C30
                         if "C30" in utter and int(utter[-9:]) >= 387:
                             new_number = int(utter[-9:]) - 387
@@ -90,22 +105,29 @@ def generate_data_files(
                             start = f"{float(start) - segment_length:.2f}"
                             end = f"{float(end) - segment_length:.2f}"
                             audio_path = os.path.join(
-                                segmented_audio_path, f"{wavID}.wav"
+                                segmented_audio_path,
+                                f"{wavID}.wav",
                             )
                         elif "C30" in utter and int(utter[-9:]) < 387:
                             utter = utter.replace("C30", "C30_P1")
                             wavID = wavID.replace("C30", "C30_P1")
                             audio_path = os.path.join(
-                                segmented_audio_path, f"{wavID}.wav"
+                                segmented_audio_path,
+                                f"{wavID}.wav",
                             )
                         else:
                             audio_path = os.path.join(
-                                edacc_root, "data", f"{wavID}.wav"
+                                edacc_root,
+                                "data",
+                                f"{wavID}.wav",
                             )
                         seg_out.write(
                             f"{utter_spk_map[utter]}-{utter} {wavID} {start} {end}\n"
                         )
-                        if os.path.exists(audio_path) and wavID not in wavID_set:
+                        if (
+                            os.path.exists(audio_path)
+                            and wavID not in wavID_set
+                        ):
                             scp_out.write(f"{wavID} {audio_path}\n")
                             wavID_set.add(wavID)
 
@@ -114,7 +136,8 @@ def generate_data_files(
 
     if len(sys.argv) != 4:
         print(
-            "Usage: python data_prep.py [edacc download directory] [target directory] [large audio path]"
+            "Usage: python data_prep.py [edacc download directory]"
+            "[target directory] [large audio path]"
         )
         sys.exit(1)
 

diff --git a/egs2/edacc/asr1/local/truncate_test.py b/egs2/edacc/asr1/local/truncate_test.py
@@ -6,12 +6,14 @@
 
 def truncate_test_set(test_dir, utterance_splits):
     """
-    Truncate specified utterances in a Kaldi test set directory and reorganize the folder.
+    Truncate specified utterances in a Kaldi test set directory.
 
     Args:
         test_dir (str): Path to the Kaldi test set directory.
-        utterance_splits (dict): A dictionary where keys are original utterance IDs, and values are lists of tuples,
-                                 each containing (new_utterance_id, start_time, end_time).
+        utterance_splits (dict):
+            A dictionary where keys are original utterance IDs,
+            and values are lists of tuples, each containing
+            (new_utterance_id, start_time, end_time).
 
     Returns:
         None
@@ -41,7 +43,12 @@ def truncate_test_set(test_dir, utterance_splits):
         for line in text_file_input:
             utter, _ = line.strip().split(maxsplit=1)
             if utter in utterance_splits:
-                for new_utter, _, _, new_txt in utterance_splits[utter]:
+                for (
+                    new_utter,
+                    _,
+                    _,
+                    new_txt,
+                ) in utterance_splits[utter]:
                     new_text.append(f"{new_utter} {new_txt}\n")
             else:
                 new_text.append(line)
@@ -50,7 +57,12 @@ def truncate_test_set(test_dir, utterance_splits):
         for line in utt2spk_file_input:
             utter, spk = line.strip().split()
             if utter in utterance_splits:
-                for new_utter, _, _, _ in utterance_splits[utter]:
+                for (
+                    new_utter,
+                    _,
+                    _,
+                    _,
+                ) in utterance_splits[utter]:
                     new_utt2spk.append(f"{new_utter} {spk}\n")
             else:
                 new_utt2spk.append(line)
@@ -59,8 +71,15 @@ def truncate_test_set(test_dir, utterance_splits):
         for line in segment_file_input:
             utter, id, start, end = line.strip().split()
             if utter in utterance_splits:
-                for new_utter, new_start, new_end, _ in utterance_splits[utter]:
-                    new_segment.append(f"{new_utter} {id} {new_start} {new_end}\n")
+                for (
+                    new_utter,
+                    new_start,
+                    new_end,
+                    _,
+                ) in utterance_splits[utter]:
+                    new_segment.append(
+                        f"{new_utter} {id} {new_start} {new_end}\n"
+                    )
             else:
                 new_segment.append(line)