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/libtorch/funasr_torch/utils/utils.py | 16 +++++-----------
1 files changed, 5 insertions(+), 11 deletions(-)
diff --git a/funasr/runtime/python/libtorch/funasr_torch/utils/utils.py b/funasr/runtime/python/libtorch/funasr_torch/utils/utils.py
index cafc43b..913ddc1 100644
--- a/funasr/runtime/python/libtorch/funasr_torch/utils/utils.py
+++ b/funasr/runtime/python/libtorch/funasr_torch/utils/utils.py
@@ -9,7 +9,6 @@
import numpy as np
import yaml
-from typeguard import check_argument_types
import warnings
@@ -21,11 +20,12 @@
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]
+
def get_num_vocabulary_size(self) -> int:
return len(self.token_list)
@@ -38,13 +38,8 @@
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():
@@ -54,7 +49,6 @@
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)
--
Gitblit v1.9.1