From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/tasks/abs_task.py | 55 ++++++++++++++++++++-----------------------------------
1 files changed, 20 insertions(+), 35 deletions(-)
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index 361ff89..f7f13d2 100644
--- a/funasr/tasks/abs_task.py
+++ b/funasr/tasks/abs_task.py
@@ -32,8 +32,6 @@
import yaml
from funasr.models.base_model import FunASRModel
from torch.utils.data import DataLoader
-from typeguard import check_argument_types
-from typeguard import check_return_type
from funasr import __version__
from funasr.datasets.dataset import AbsDataset
@@ -73,6 +71,7 @@
from funasr.utils.types import str_or_none
from funasr.utils.wav_utils import calc_shape, generate_data_list, filter_wav_text
from funasr.utils.yaml_no_alias_safe_dump import yaml_no_alias_safe_dump
+from funasr.modules.lora.utils import mark_only_lora_as_trainable
try:
import wandb
@@ -266,9 +265,9 @@
def build_model(cls, args: argparse.Namespace) -> FunASRModel:
raise NotImplementedError
+
@classmethod
def get_parser(cls) -> config_argparse.ArgumentParser:
- assert check_argument_types()
class ArgumentDefaultsRawTextHelpFormatter(
argparse.RawTextHelpFormatter,
@@ -954,11 +953,22 @@
default=None,
help="oss bucket.",
)
+ group.add_argument(
+ "--enable_lora",
+ type=str2bool,
+ default=False,
+ help="Apply lora for finetuning.",
+ )
+ group.add_argument(
+ "--lora_bias",
+ type=str,
+ default="none",
+ help="lora bias.",
+ )
cls.trainer.add_arguments(parser)
cls.add_task_arguments(parser)
- assert check_return_type(parser)
return parser
@classmethod
@@ -1006,7 +1016,6 @@
return _cls
# This method is used only for --print_config
- assert check_argument_types()
parser = cls.get_parser()
args, _ = parser.parse_known_args()
config = vars(args)
@@ -1046,7 +1055,6 @@
@classmethod
def check_required_command_args(cls, args: argparse.Namespace):
- assert check_argument_types()
if hasattr(args, "required"):
for k in vars(args):
if "-" in k:
@@ -1076,7 +1084,6 @@
inference: bool = False,
) -> None:
"""Check if the dataset satisfy the requirement of current Task"""
- assert check_argument_types()
mes = (
f"If you intend to use an additional input, modify "
f'"{cls.__name__}.required_data_names()" or '
@@ -1103,14 +1110,12 @@
@classmethod
def print_config(cls, file=sys.stdout) -> None:
- assert check_argument_types()
# Shows the config: e.g. python train.py asr --print_config
config = cls.get_default_config()
file.write(yaml_no_alias_safe_dump(config, indent=4, sort_keys=False))
@classmethod
def main(cls, args: argparse.Namespace = None, cmd: Sequence[str] = None):
- assert check_argument_types()
print(get_commandline_args(), file=sys.stderr)
if args is None:
parser = cls.get_parser()
@@ -1147,7 +1152,6 @@
@classmethod
def main_worker(cls, args: argparse.Namespace):
- assert check_argument_types()
# 0. Init distributed process
distributed_option = build_dataclass(DistributedOption, args)
@@ -1255,6 +1259,8 @@
dtype=getattr(torch, args.train_dtype),
device="cuda" if args.ngpu > 0 else "cpu",
)
+ if args.enable_lora:
+ mark_only_lora_as_trainable(model, args.lora_bias)
for t in args.freeze_param:
for k, p in model.named_parameters():
if k.startswith(t + ".") or k == t:
@@ -1375,25 +1381,10 @@
# 7. Build iterator factories
if args.dataset_type == "large":
- 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,
- 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,
- 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")
+ from funasr.datasets.large_datasets.build_dataloader import LargeDataLoader
+ train_iter_factory = LargeDataLoader(args, mode="train")
+ valid_iter_factory = LargeDataLoader(args, mode="eval")
+
elif args.dataset_type == "small":
train_iter_factory = cls.build_iter_factory(
args=args,
@@ -1570,7 +1561,6 @@
- 4 epoch with "--num_iters_per_epoch" == 4
"""
- assert check_argument_types()
iter_options = cls.build_iter_options(args, distributed_option, mode)
# Overwrite iter_options if any kwargs is given
@@ -1603,7 +1593,6 @@
def build_sequence_iter_factory(
cls, args: argparse.Namespace, iter_options: IteratorOptions, mode: str
) -> AbsIterFactory:
- assert check_argument_types()
if hasattr(args, "frontend_conf"):
if args.frontend_conf is not None and "fs" in args.frontend_conf:
@@ -1697,7 +1686,6 @@
iter_options: IteratorOptions,
mode: str,
) -> AbsIterFactory:
- assert check_argument_types()
dataset = ESPnetDataset(
iter_options.data_path_and_name_and_type,
@@ -1802,7 +1790,6 @@
def build_multiple_iter_factory(
cls, args: argparse.Namespace, distributed_option: DistributedOption, mode: str
):
- assert check_argument_types()
iter_options = cls.build_iter_options(args, distributed_option, mode)
assert len(iter_options.data_path_and_name_and_type) > 0, len(
iter_options.data_path_and_name_and_type
@@ -1899,7 +1886,6 @@
inference: bool = False,
) -> DataLoader:
"""Build DataLoader using iterable dataset"""
- assert check_argument_types()
# For backward compatibility for pytorch DataLoader
if collate_fn is not None:
kwargs = dict(collate_fn=collate_fn)
@@ -1949,7 +1935,6 @@
device: Device type, "cpu", "cuda", or "cuda:N".
"""
- assert check_argument_types()
if config_file is None:
assert model_file is not None, (
"The argument 'model_file' must be provided "
--
Gitblit v1.9.1