pre-commit autoupdate && pre-commit run --all-files

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v5.0.0
     hooks:
       - id: check-json
       - id: end-of-file-fixer
@@ -11,17 +11,17 @@ repos:
       - id: check-added-large-files
         args: [--maxkb=4096]
   - repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 24.10.0
     hooks:
       - id: black
   - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
       - id: isort
         name: isort (python)
         args: ["--profile", "black", "-l", "88", "--trailing-comma", "--multi-line", "3"]
   - repo: https://github.com/pycqa/flake8.git
-    rev: 6.0.0
+    rev: 7.1.1
     hooks:
       - id: flake8
         types: [python]

whisper/normalizers/basic.py

@@ -30,15 +30,19 @@ def remove_symbols_and_diacritics(s: str, keep=""):
     and drop any diacritics (category 'Mn' and some manual mappings)
     """
     return "".join(
+        (
             c
             if c in keep
-        else ADDITIONAL_DIACRITICS[c]
+            else (
+                ADDITIONAL_DIACRITICS[c]
                 if c in ADDITIONAL_DIACRITICS
-        else ""
+                else (
+                    ""
                     if unicodedata.category(c) == "Mn"
-        else " "
-        if unicodedata.category(c)[0] in "MSP"
-        else c
+                    else " " if unicodedata.category(c)[0] in "MSP" else c
+                )
+            )
+        )
         for c in unicodedata.normalize("NFKD", s)
     )
 

whisper/utils.py

@@ -209,9 +209,11 @@ class SubtitlesWriter(ResultWriter):
 
                         yield start, end, "".join(
                             [
+                                (
                                     re.sub(r"^(\s*)(.*)$", r"\1<u>\2</u>", word)
                                     if j == i
                                     else word
+                                )
                                 for j, word in enumerate(all_words)
                             ]
                         )