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.

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

support icmc eval track 1 #1235

Merged
merged 1 commit into from
Dec 14, 2023
Merged
Changes from all commits
Commits
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
10 changes: 8 additions & 2 deletions lhotse/recipes/icmcasr.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,11 @@
from lhotse.supervision import SupervisionSegment, SupervisionSet
from lhotse.utils import Pathlike, is_module_available

ICMCASR = ("train", "dev") # TODO: Support all subsets when released
ICMCASR = (
"train",
"dev",
"eval_track1",
) # TODO: Support eval2 by people who have access to it.
POSITION = ("DA01", "DA02", "DA03", "DA04")
# ignore "DX05C01", "DX06C01",
# which are 2-channel reference signals for AEC.
Expand Down Expand Up @@ -124,7 +128,7 @@ def _parse_utterance(
end = interval.maxTime
text = interval.mark
segment = SupervisionSegment(
id=f"{recording_id}-{i}",
id=f"{recording_id}-{round(start * 1000):06}-{round(end * 1000):06}",
recording_id=recording_id,
start=start,
duration=round(end - start, 4),
Expand Down Expand Up @@ -199,6 +203,8 @@ def prepare_icmcasr(
logging.info("Preparing ICMC-ASR...")

subsets = ICMCASR
if mic == "ihm":
subsets = ("train", "dev")

if output_dir is not None:
output_dir = Path(output_dir)
Expand Down
Loading