mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

from local

Browse Source
This commit is contained in:
dohe0342 2022-12-22 16:26:15 +09:00
parent fc187b5077
commit 896317d589
2 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
egs/librispeech/ASR/pruned_transducer_stateless6/.train.py.swp
View File

Binary file not shown.

8
egs/librispeech/ASR/pruned_transducer_stateless6/train.py
View File

@ -985,9 +985,11 @@ def run(rank, world_size, args):
# an utterance duration distribution for your dataset to select # an utterance duration distribution for your dataset to select
# the threshold # the threshold
if c.duration < 1.0 or c.duration > 20.0: if c.duration < 1.0 or c.duration > 20.0:
'''
logging.warning( logging.warning(
f"Exclude cut with ID {c.id} from training. Duration: {c.duration}" f"Exclude cut with ID {c.id} from training. Duration: {c.duration}"
) )
'''
return False return False
# In pruned RNN-T, we require that T >= S # In pruned RNN-T, we require that T >= S
@ -998,8 +1000,9 @@ def run(rank, world_size, args):
# for subsampling # for subsampling
T = ((c.num_frames - 1) // 2 - 1) // 2 T = ((c.num_frames - 1) // 2 - 1) // 2
tokens = sp.encode(c.supervisions[0].text, out_type=str) tokens = sp.encode(c.supervisions[0].text, out_type=str)
if T < len(tokens): if T < len(tokens):
'''
logging.warning( logging.warning(
f"Exclude cut with ID {c.id} from training. " f"Exclude cut with ID {c.id} from training. "
f"Number of frames (before subsampling): {c.num_frames}. " f"Number of frames (before subsampling): {c.num_frames}. "
@ -1008,8 +1011,9 @@ def run(rank, world_size, args):
f"Tokens: {tokens}. " f"Tokens: {tokens}. "
f"Number of tokens: {len(tokens)}" f"Number of tokens: {len(tokens)}"
) )
'''
return False return False
return True return True
train_cuts = train_cuts.filter(remove_short_and_long_utt) train_cuts = train_cuts.filter(remove_short_and_long_utt)