Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Decoding improvements #1033

Merged
merged 2 commits into from
Mar 6, 2023
Merged

Decoding improvements #1033

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bbd0d6f
suppress task tokens (transcribe/translate)
jongwook Mar 6, 2023
f042dcf
not ignoring the last segment ending with one timestamp
jongwook Mar 6, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
not ignoring the last segment ending with one timestamp
  • Loading branch information
@jongwook
jongwook committed Mar 6, 2023
commit f042dcfa34de3a24055d5aded1a7e1c69db0c798
30 changes: 15 additions & 15 deletions whisper/transcribe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,35 +197,35 @@ def add_segment(
timestamp_tokens: torch.Tensor = tokens.ge(tokenizer.timestamp_begin)
consecutive = torch.where(timestamp_tokens[:-1] & timestamp_tokens[1:])[0].add_(1)
if len(consecutive) > 0: # if the output contains two consecutive timestamp tokens
if ended_with_single_timestamp := timestamp_tokens[-2:].tolist() == [False, True]:
consecutive = consecutive.tolist() + [len(tokens)]
last_slice = 0
for current_slice in consecutive:
sliced_tokens = tokens[last_slice:current_slice]
start_timestamp_position = (
sliced_tokens[0].item() - tokenizer.timestamp_begin
)
end_timestamp_position = (
sliced_tokens[-1].item() - tokenizer.timestamp_begin
)
start_timestamp_pos = sliced_tokens[0].item() - tokenizer.timestamp_begin
end_timestamp_pos = sliced_tokens[-1].item() - tokenizer.timestamp_begin
add_segment(
start=timestamp_offset + start_timestamp_position * time_precision,
end=timestamp_offset + end_timestamp_position * time_precision,
start=timestamp_offset + start_timestamp_pos * time_precision,
end=timestamp_offset + end_timestamp_pos * time_precision,
text_tokens=sliced_tokens[1:-1],
result=result,
)
last_slice = current_slice
last_timestamp_position = (
tokens[last_slice - 1].item() - tokenizer.timestamp_begin
)
seek += last_timestamp_position * input_stride
if ended_with_single_timestamp:
# single timestamp at the end means no speech after the last timestamp.
seek += segment.shape[-1]
else:
# otherwise, ignore the unfinished segment and seek to the last timestamp
last_timestamp_pos = tokens[last_slice - 1].item() - tokenizer.timestamp_begin
seek += last_timestamp_pos * input_stride
all_tokens.extend(tokens[: last_slice + 1].tolist())
else:
duration = segment_duration
timestamps = tokens[timestamp_tokens.nonzero().flatten()]
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
duration = last_timestamp_position * time_precision
last_timestamp_pos = timestamps[-1].item() - tokenizer.timestamp_begin
duration = last_timestamp_pos * time_precision

add_segment(
start=timestamp_offset,
Expand Down