File size: 1,503 Bytes
7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 f8a9c31 7c89374 | 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 | # processing_mini_whisper.py
from ...processing_utils import ProcessorMixin
from ...utils import auto_docstring
@auto_docstring
class MiniWhisperProcessor(ProcessorMixin):
def __init__(self, feature_extractor, tokenizer):
super().__init__(feature_extractor, tokenizer)
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 get_prompt_ids(self, text: str, return_tensors="np"):
return self.tokenizer.get_prompt_ids(text, return_tensors=return_tensors)
@auto_docstring
def __call__(self, *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
__all__ = ["MiniWhisperProcessor"] |