mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-09 14:05:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make the probability to select a batch from GigaSpeech configurable.

Browse Source
This commit is contained in:
Fangjun Kuang 2022-02-17 18:34:48 +08:00
parent 981bf74364
commit 61b0019ffd
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
egs/librispeech/ASR/transducer_stateless_multi_datasets/train.py
View File

@ -161,6 +161,13 @@ def get_parser():
""",
)
parser.add_argument(
"--giga-prob",
type=float,
default=0.2,
help="The probability to select a batch from the GigaSpeech dataset",
)
return parser
@ -523,7 +530,7 @@ def train_one_epoch(
# index 0: for LibriSpeech
# index 1: for GigaSpeech
# This sets the probabilities for choosing which datasets
dl_weights = [0.8, 0.2]
dl_weights = [1 - params.giga_prob, params.giga_prob]
iter_libri = iter(train_dl)
iter_giga = iter(giga_train_dl)
@ -861,6 +868,8 @@ def main():
args = parser.parse_args()
args.exp_dir = Path(args.exp_dir)
assert 0 < args.giga_prob < 1, args.giga_prob
world_size = args.world_size
assert world_size >= 1
if world_size > 1: