Word timing tweaks (#616)

AIXerum · Dec 13, 2023 · 8a58422 · 8a58422
1 parent c869be9
commit 8a58422
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/faster_whisper/transcribe.py b/faster_whisper/transcribe.py
@@ -908,6 +908,13 @@ def find_alignment(
         words, word_tokens = tokenizer.split_to_word_tokens(
             text_tokens + [tokenizer.eot]
         )
+        if len(word_tokens) <= 1:
+            # return on eot only
+            # >>> np.pad([], (1, 0))
+            # array([0.])
+            # This results in crashes when we lookup jump_times with float, like
+            # IndexError: arrays used as indices must be of integer (or boolean) type
+            return []
         word_boundaries = np.pad(np.cumsum([len(t) for t in word_tokens[:-1]]), (1, 0))
         if len(word_boundaries) <= 1:
             return []