Given a list of groups of samples and their cumulative log probabilities, return the indices of the samples in each group to select a

Update the key-value cache according to the updated beams

Replace any other markers, symbols, and punctuations with a space, and drop any diacritics (category 'Mn' and some manual mappings)

Initialize any stateful variables for decoding a new sequence

Constructs a ResNet-50 model_hyper. Args: pretrained (bool): If True, returns a model_hyper pre-trained on ImageNet

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to

Set the number of features diminsions. Args: num_features: Number of features diminsions.

Returns sinusoids for positional embedding

Transcribe an audio file using Whisper Parameters ---------- model: Whisper The Whisper model instance audio: Union[str

Write a transcript to a file in SRT format. Example usage: from pathlib import Path from whisper.utils import write_srt

Get audio samples and video frame at `idx`. Parameters ---------- idx : int or slice The frame index, can be nega