mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-09 05:55:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge d400bc5edf3a3510d29497b9a7b6b1d1d8eb730d into 0904e490c5fb424dc5cb4d14ae468e4d32a07dc4

Browse Source
This commit is contained in:
Karel Vesely 2025-11-28 11:00:32 +05:30 committed by GitHub
commit 8ba5b87ca0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
egs/librispeech/ASR/zipformer/train.py
View File

@ -1409,9 +1409,11 @@ def run(rank, world_size, args):
T = ((c.num_frames - 7) // 2 + 1) // 2
tokens = sp.encode(c.supervisions[0].text, out_type=str)
if T < len(tokens):
# For CTC `(T - 2) < len(tokens)` is needed. otherwise inf. in loss appears.
# For Transducer `T < len(tokens)` was okay.
if (T - 2) < len(tokens):
logging.warning(
f"Exclude cut with ID {c.id} from training. "
f"Exclude cut with ID {c.id} from training (too many supervision tokens). "
f"Number of frames (before subsampling): {c.num_frames}. "
f"Number of frames (after subsampling): {T}. "
f"Text: {c.supervisions[0].text}. "