|
@@ -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
|