Use Python 3.9 syntax in tests (#37343)

Signed-off-by: cyy <cyyever@outlook.com>
This commit is contained in:
cyyever
2025-04-08 20:12:08 +08:00
committed by GitHub
parent 0fc683d1cd
commit 1e6b546ea6
666 changed files with 265 additions and 946 deletions

View File

@@ -1,4 +1,3 @@
# coding=utf-8
# Copyright 2021 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
@@ -18,7 +17,6 @@ import json
import os
import unittest
from functools import lru_cache
from typing import Tuple
from transformers import Wav2Vec2PhonemeCTCTokenizer
from transformers.models.wav2vec2.tokenization_wav2vec2 import VOCAB_FILES_NAMES
@@ -62,7 +60,7 @@ class Wav2Vec2PhonemeCTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
fp.write(json.dumps(vocab_tokens) + "\n")
# overwrite since phonemes require specific creation
def get_clean_sequence(self, tokenizer, with_prefix_space=False, max_length=20, min_length=5) -> Tuple[str, list]:
def get_clean_sequence(self, tokenizer, with_prefix_space=False, max_length=20, min_length=5) -> tuple[str, list]:
toks = [(i, tokenizer.decode([i], clean_up_tokenization_spaces=False)) for i in range(len(tokenizer))]
toks = list(filter(lambda t: [t[0]] == tokenizer.encode(t[1], do_phonemize=False), toks))
if max_length is not None and len(toks) > max_length: