/
processing_speech_to_text_2.py
115 lines (100 loc) 路 4.68 KB
/
processing_speech_to_text_2.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
# coding=utf-8
# Copyright 2021 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Speech processor class for Speech2Text2
"""
import warnings
from contextlib import contextmanager
from ...processing_utils import ProcessorMixin
class Speech2Text2Processor(ProcessorMixin):
r"""
Constructs a Speech2Text2 processor which wraps a Speech2Text2 feature extractor and a Speech2Text2 tokenizer into
a single processor.
[`Speech2Text2Processor`] offers all the functionalities of [`AutoFeatureExtractor`] and [`Speech2Text2Tokenizer`].
See the [`~Speech2Text2Processor.__call__`] and [`~Speech2Text2Processor.decode`] for more information.
Args:
feature_extractor (`AutoFeatureExtractor`):
An instance of [`AutoFeatureExtractor`]. The feature extractor is a required input.
tokenizer (`Speech2Text2Tokenizer`):
An instance of [`Speech2Text2Tokenizer`]. The tokenizer is a required input.
"""
feature_extractor_class = "AutoFeatureExtractor"
tokenizer_class = "Speech2Text2Tokenizer"
def __init__(self, feature_extractor, tokenizer):
super().__init__(feature_extractor, tokenizer)
self.current_processor = self.feature_extractor
self._in_target_context_manager = False
def __call__(self, *args, **kwargs):
"""
When used in normal mode, this method forwards all its arguments to AutoFeatureExtractor's
[`~AutoFeatureExtractor.__call__`] and returns its output. If used in the context
[`~Speech2Text2Processor.as_target_processor`] this method forwards all its arguments to
Speech2Text2Tokenizer's [`~Speech2Text2Tokenizer.__call__`]. Please refer to the doctsring of the above two
methods for more information.
"""
# For backward compatibility
if self._in_target_context_manager:
return self.current_processor(*args, **kwargs)
if "raw_speech" in kwargs:
warnings.warn("Using `raw_speech` as a keyword argument is deprecated. Use `audio` instead.")
audio = kwargs.pop("raw_speech")
else:
audio = kwargs.pop("audio", None)
sampling_rate = kwargs.pop("sampling_rate", None)
text = kwargs.pop("text", None)
if len(args) > 0:
audio = args[0]
args = args[1:]
if audio is None and text is None:
raise ValueError("You need to specify either an `audio` or `text` input to process.")
if audio is not None:
inputs = self.feature_extractor(audio, *args, sampling_rate=sampling_rate, **kwargs)
if text is not None:
encodings = self.tokenizer(text, **kwargs)
if text is None:
return inputs
elif audio is None:
return encodings
else:
inputs["labels"] = encodings["input_ids"]
return inputs
def batch_decode(self, *args, **kwargs):
"""
This method forwards all its arguments to Speech2Text2Tokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please
refer to the docstring of this method for more information.
"""
return self.tokenizer.batch_decode(*args, **kwargs)
def decode(self, *args, **kwargs):
"""
This method forwards all its arguments to Speech2Text2Tokenizer's [`~PreTrainedTokenizer.decode`]. Please refer
to the docstring of this method for more information.
"""
return self.tokenizer.decode(*args, **kwargs)
@contextmanager
def as_target_processor(self):
"""
Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning
Speech2Text2.
"""
warnings.warn(
"`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your "
"labels by using the argument `text` of the regular `__call__` method (either in the same call as "
"your audio inputs, or in a separate call."
)
self._in_target_context_manager = True
self.current_processor = self.tokenizer
yield
self.current_processor = self.feature_extractor
self._in_target_context_manager = False