From bc723ea200144bd6fa8a5dff4b9a780feda144fc Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 29 六月 2023 18:55:01 +0800
Subject: [PATCH] dcos

---
 funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py |   27 +++++----------------------
 1 files changed, 5 insertions(+), 22 deletions(-)

diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
index 0df954e..9284943 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
@@ -10,7 +10,6 @@
 import yaml
 from onnxruntime import (GraphOptimizationLevel, InferenceSession,
                          SessionOptions, get_available_providers, get_device)
-from typeguard import check_argument_types
 
 import warnings
 
@@ -22,23 +21,12 @@
 class TokenIDConverter():
     def __init__(self, token_list: Union[List, str],
                  ):
-        check_argument_types()
 
-        # self.token_list = self.load_token(token_path)
         self.token_list = token_list
         self.unk_symbol = token_list[-1]
+        self.token2id = {v: i for i, v in enumerate(self.token_list)}
+        self.unk_id = self.token2id[self.unk_symbol]
 
-    # @staticmethod
-    # def load_token(file_path: Union[Path, str]) -> List:
-    #     if not Path(file_path).exists():
-    #         raise TokenIDConverterError(f'The {file_path} does not exist.')
-    #
-    #     with open(str(file_path), 'rb') as f:
-    #         token_list = pickle.load(f)
-    #
-    #     if len(token_list) != len(set(token_list)):
-    #         raise TokenIDConverterError('The Token exists duplicated symbol.')
-    #     return token_list
 
     def get_num_vocabulary_size(self) -> int:
         return len(self.token_list)
@@ -51,13 +39,8 @@
         return [self.token_list[i] for i in integers]
 
     def tokens2ids(self, tokens: Iterable[str]) -> List[int]:
-        token2id = {v: i for i, v in enumerate(self.token_list)}
-        if self.unk_symbol not in token2id:
-            raise TokenIDConverterError(
-                f"Unknown symbol '{self.unk_symbol}' doesn't exist in the token_list"
-            )
-        unk_id = token2id[self.unk_symbol]
-        return [token2id.get(i, unk_id) for i in tokens]
+
+        return [self.token2id.get(i, self.unk_id) for i in tokens]
 
 
 class CharTokenizer():
@@ -67,7 +50,6 @@
         space_symbol: str = "<space>",
         remove_non_linguistic_symbols: bool = False,
     ):
-        check_argument_types()
 
         self.space_symbol = space_symbol
         self.non_linguistic_symbols = self.load_symbols(symbol_value)
@@ -286,4 +268,5 @@
     logger.addHandler(sh)
     logger_initialized[name] = True
     logger.propagate = False
+    logging.basicConfig(level=logging.ERROR)
     return logger

--
Gitblit v1.9.1