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