From 24f73665e2d8ea8e4de2fe4f900bc539d7f7b989 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 17 四月 2023 15:49:45 +0800
Subject: [PATCH] Merge pull request #367 from alibaba-damo-academy/dev_lhn2
---
funasr/tasks/abs_task.py | 30 +++++++++++++++++++++++++-----
1 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index 3f20b4f..777513e 100644
--- a/funasr/tasks/abs_task.py
+++ b/funasr/tasks/abs_task.py
@@ -464,6 +464,12 @@
default=sys.maxsize,
help="The maximum number update step to train",
)
+ parser.add_argument(
+ "--batch_interval",
+ type=int,
+ default=10000,
+ help="The batch interval for saving model.",
+ )
group.add_argument(
"--patience",
type=int_or_none,
@@ -1193,12 +1199,18 @@
# logging.basicConfig() is invoked in main_worker() instead of main()
# because it can be invoked only once in a process.
# FIXME(kamo): Should we use logging.getLogger()?
+ # BUGFIX: Remove previous handlers and reset log level
+ for handler in logging.root.handlers[:]:
+ logging.root.removeHandler(handler)
logging.basicConfig(
level=args.log_level,
format=f"[{os.uname()[1].split('.')[0]}]"
f" %(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
else:
+ # BUGFIX: Remove previous handlers and reset log level
+ for handler in logging.root.handlers[:]:
+ logging.root.removeHandler(handler)
# Suppress logging if RANK != 0
logging.basicConfig(
level="ERROR",
@@ -1349,15 +1361,15 @@
from funasr.datasets.large_datasets.build_dataloader import ArkDataLoader
train_iter_factory = ArkDataLoader(args.train_data_file, args.token_list, args.dataset_conf,
frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
- seg_dict_file=args.seg_dict_file if hasattr(args,
- "seg_dict_file") else None,
+ seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None,
punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
+ bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None,
mode="train")
valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
- seg_dict_file=args.seg_dict_file if hasattr(args,
- "seg_dict_file") else None,
+ seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None,
punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
+ bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None,
mode="eval")
elif args.dataset_type == "small":
train_iter_factory = cls.build_iter_factory(
@@ -1570,13 +1582,21 @@
) -> AbsIterFactory:
assert check_argument_types()
+ if hasattr(args, "frontend_conf"):
+ if args.frontend_conf is not None and "fs" in args.frontend_conf:
+ dest_sample_rate = args.frontend_conf["fs"]
+ else:
+ dest_sample_rate = 16000
+ else:
+ dest_sample_rate = 16000
+
dataset = ESPnetDataset(
iter_options.data_path_and_name_and_type,
float_dtype=args.train_dtype,
preprocess=iter_options.preprocess_fn,
max_cache_size=iter_options.max_cache_size,
max_cache_fd=iter_options.max_cache_fd,
- dest_sample_rate=args.frontend_conf["fs"],
+ dest_sample_rate=dest_sample_rate,
)
cls.check_task_requirements(
dataset, args.allow_variable_data_keys, train=iter_options.train
--
Gitblit v1.9.1