99 lines
3.8 KiB
Python
99 lines
3.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2022 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 Whisper
|
|
"""
|
|
|
|
|
|
from ...processing_utils import ProcessorMixin
|
|
|
|
|
|
class WhisperProcessor(ProcessorMixin):
|
|
r"""
|
|
Constructs a Whisper processor which wraps a Whisper feature extractor and a Whisper tokenizer into a single
|
|
processor.
|
|
|
|
[`WhisperProcessor`] offers all the functionalities of [`WhisperFeatureExtractor`] and [`WhisperTokenizer`]. See
|
|
the [`~WhisperProcessor.__call__`] and [`~WhisperProcessor.decode`] for more information.
|
|
|
|
Args:
|
|
feature_extractor (`WhisperFeatureExtractor`):
|
|
An instance of [`WhisperFeatureExtractor`]. The feature extractor is a required input.
|
|
tokenizer (`WhisperTokenizer`):
|
|
An instance of [`WhisperTokenizer`]. The tokenizer is a required input.
|
|
"""
|
|
|
|
feature_extractor_class = "WhisperFeatureExtractor"
|
|
tokenizer_class = "WhisperTokenizer"
|
|
|
|
def __init__(self, feature_extractor, tokenizer):
|
|
super().__init__(feature_extractor, tokenizer)
|
|
self.current_processor = self.feature_extractor
|
|
self._in_target_context_manager = False
|
|
|
|
def get_decoder_prompt_ids(self, task=None, language=None, no_timestamps=True):
|
|
return self.tokenizer.get_decoder_prompt_ids(task=task, language=language, no_timestamps=no_timestamps)
|
|
|
|
def __call__(self, *args, **kwargs):
|
|
"""
|
|
Forwards the `audio` argument to WhisperFeatureExtractor's [`~WhisperFeatureExtractor.__call__`] and the `text`
|
|
argument to [`~WhisperTokenizer.__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)
|
|
|
|
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 WhisperTokenizer'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 WhisperTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
|
|
the docstring of this method for more information.
|
|
"""
|
|
return self.tokenizer.decode(*args, **kwargs)
|
|
|
|
def get_prompt_ids(self, text: str, return_tensors="np"):
|
|
return self.tokenizer.get_prompt_ids(text, return_tensors=return_tensors)
|