From fac8dbd8210406b95d8b7d43e5ca540ac5cb1995 Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 20 四月 2023 17:36:49 +0800
Subject: [PATCH] update
---
funasr/build_utils/build_args.py | 134 +++-----------------------------------------
1 files changed, 10 insertions(+), 124 deletions(-)
diff --git a/funasr/build_utils/build_args.py b/funasr/build_utils/build_args.py
index 91f2810..fc737ba 100644
--- a/funasr/build_utils/build_args.py
+++ b/funasr/build_utils/build_args.py
@@ -17,12 +17,6 @@
# 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,
default=True,
@@ -33,20 +27,6 @@
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",
@@ -61,31 +41,12 @@
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:
@@ -93,101 +54,26 @@
# 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)
- parser.add_argument(
- "--token_list",
- type=str_or_none,
- default=None,
- help="A text mapping int-id to token",
- )
- 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 == "punc":
+ from funasr.build_utils.build_punc_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)
+
else:
raise NotImplementedError("Not supported task: {}".format(args.task_name))
--
Gitblit v1.9.1