sima_utils.transformer.model.whisper_decoder_cache_model

Classes

WhisperDecoderCacheModel

Implementation for the cache model of Whisper.

Module Contents

class sima_utils.transformer.model.whisper_decoder_cache_model.WhisperDecoderCacheModel

Implementation for the cache model of Whisper.

This implements a simplified version of the LanguageCacheModel. This model is only used when generating new tokens so the num_tokens is assumed to be 1.

num_tokens

Number of tokens. Set to a value greater than 1 to consume multiple input tokens in one model.

token_idx

Token index.

num_tokens: int
token_idx: int
use_future_token_mask: bool
gen_onnx_files()