Don't update duration if last timestamp is same as begin (#191)

2022-09-29 15:27:48 -04:00
parent 62fe7f1009
commit 2b0c2971af
1 changed files with 1 additions and 1 deletions
--- a/whisper/transcribe.py
+++ b/whisper/transcribe.py
@@ -220,7 +220,7 @@ def transcribe(
            else:
                duration = segment_duration
                timestamps = tokens[timestamp_tokens.nonzero().flatten()]
-                if len(timestamps) > 0:
+                if len(timestamps) > 0 and timestamps[-1].item() != tokenizer.timestamp_begin:
                    # no consecutive timestamps but it has a timestamp; use the last one.
                    # single timestamp at the end means no speech after the last timestamp.
                    last_timestamp_position = timestamps[-1].item() - tokenizer.timestamp_begin