From abde816a6cd393697eac6ffea300061ec0ed8aae Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 17:08:28 +0800
Subject: [PATCH] update
---
funasr/build_utils/build_args.py | 159 ++++++++--------------------------------------------
1 files changed, 26 insertions(+), 133 deletions(-)
diff --git a/funasr/build_utils/build_args.py b/funasr/build_utils/build_args.py
index 91f2810..a50122d 100644
--- a/funasr/build_utils/build_args.py
+++ b/funasr/build_utils/build_args.py
@@ -1,6 +1,5 @@
-import argparse
-
from funasr.models.ctc import CTC
+from funasr.utils import config_argparse
from funasr.utils.get_default_kwargs import get_default_kwargs
from funasr.utils.nested_dict_action import NestedDictAction
from funasr.utils.types import int_or_none
@@ -8,20 +7,12 @@
from funasr.utils.types import str_or_none
-def build_args(args):
- parser = argparse.ArgumentParser("Task related config")
+def build_args(args, extra_task_params):
+ parser = config_argparse.ArgumentParser("Task related config")
if args.task_name == "asr":
from funasr.build_utils.build_asr_model import class_choices_list
for class_choices in class_choices_list:
- # Append --<name> and --<name>_conf.
- # e.g. --encoder and --encoder_conf
class_choices.add_arguments(parser)
- parser.add_argument(
- "--token_list",
- type=str_or_none,
- default=None,
- help="A text mapping int-id to token",
- )
parser.add_argument(
"--split_with_space",
type=str2bool,
@@ -33,20 +24,6 @@
type=str,
default=None,
help="seg_dict_file for text processing",
- )
- parser.add_argument(
- "--init",
- type=lambda x: str_or_none(x.lower()),
- default=None,
- help="The initialization method",
- choices=[
- "chainer",
- "xavier_uniform",
- "xavier_normal",
- "kaiming_uniform",
- "kaiming_normal",
- None,
- ],
)
parser.add_argument(
"--input_size",
@@ -61,135 +38,51 @@
help="The keyword arguments for CTC class.",
)
parser.add_argument(
- "--token_type",
- type=str,
- default="bpe",
- choices=["bpe", "char", "word", "phn"],
- help="The text will be tokenized " "in the specified level token",
- )
- parser.add_argument(
- "--bpemodel",
- type=str_or_none,
- default=None,
- help="The model file of sentencepiece",
- )
- parser.add_argument(
- "--cleaner",
- type=str_or_none,
- choices=[None, "tacotron", "jaconv", "vietnamese"],
- default=None,
- help="Apply text cleaning",
- )
- parser.add_argument(
"--cmvn_file",
type=str_or_none,
default=None,
help="The file path of noise scp file.",
)
+
elif args.task_name == "pretrain":
from funasr.build_utils.build_pretrain_model import class_choices_list
for class_choices in class_choices_list:
- # Append --<name> and --<name>_conf.
- # e.g. --encoder and --encoder_conf
class_choices.add_arguments(parser)
- parser.add_argument(
- "--init",
- type=lambda x: str_or_none(x.lower()),
- default=None,
- help="The initialization method",
- choices=[
- "chainer",
- "xavier_uniform",
- "xavier_normal",
- "kaiming_uniform",
- "kaiming_normal",
- None,
- ],
- )
parser.add_argument(
"--input_size",
type=int_or_none,
default=None,
help="The number of input dimension of the feature",
)
- parser.add_argument(
- "--feats_type",
- type=str,
- default='fbank',
- help="feats type, e.g. fbank, wav, ark_wav(needed to be scale normalization)",
- )
- parser.add_argument(
- "--noise_db_range",
- type=str,
- default="13_15",
- help="The range of noise decibel level.",
- )
- parser.add_argument(
- "--pred_masked_weight",
- type=float,
- default=1.0,
- help="weight for predictive loss for masked frames",
- )
- parser.add_argument(
- "--pred_nomask_weight",
- type=float,
- default=0.0,
- help="weight for predictive loss for unmasked frames",
- )
- parser.add_argument(
- "--loss_weights",
- type=float,
- default=0.0,
- help="weights for additional loss terms (not first one)",
- )
+
elif args.task_name == "lm":
from funasr.build_utils.build_lm_model import class_choices_list
for class_choices in class_choices_list:
- # Append --<name> and --<name>_conf.
- # e.g. --encoder and --encoder_conf
+ class_choices.add_arguments(parser)
+
+ elif args.task_name == "punc":
+ from funasr.build_utils.build_punc_model import class_choices_list
+ for class_choices in class_choices_list:
+ class_choices.add_arguments(parser)
+
+ elif args.task_name == "vad":
+ from funasr.build_utils.build_vad_model import class_choices_list
+ for class_choices in class_choices_list:
class_choices.add_arguments(parser)
parser.add_argument(
- "--token_list",
- type=str_or_none,
+ "--input_size",
+ type=int_or_none,
default=None,
- help="A text mapping int-id to token",
+ help="The number of input dimension of the feature",
)
- parser.add_argument(
- "--init",
- type=lambda x: str_or_none(x.lower()),
- default=None,
- help="The initialization method",
- choices=[
- "chainer",
- "xavier_uniform",
- "xavier_normal",
- "kaiming_uniform",
- "kaiming_normal",
- None,
- ],
- )
- parser.add_argument(
- "--token_type",
- type=str,
- default="bpe",
- choices=["bpe", "char", "word"],
- help="",
- )
- parser.add_argument(
- "--bpemodel",
- type=str_or_none,
- default=None,
- help="The model file fo sentencepiece",
- )
- parser.add_argument(
- "--cleaner",
- type=str_or_none,
- choices=[None, "tacotron", "jaconv", "vietnamese"],
- default=None,
- help="Apply text cleaning",
- )
+
+ elif args.task_name == "diar":
+ from funasr.build_utils.build_diar_model import class_choices_list
+ for class_choices in class_choices_list:
+ class_choices.add_arguments(parser)
+
else:
raise NotImplementedError("Not supported task: {}".format(args.task_name))
- args = parser.parse_args()
- return args
+ task_args = parser.parse_args(extra_task_params)
+ return task_args
--
Gitblit v1.9.1