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