in whisper/decoding.py [0:0]
def logits(self, tokens: Tensor, audio_features: Tensor) -> Tensor:
if not self.kv_cache:
self.kv_cache, self.hooks = self.model.install_kv_cache_hooks()
if tokens.shape[-1] > self.initial_token_length:
# only need to use the last token except in the first forward pass
tokens = tokens[:, -1:]
return self.model.decoder(tokens, audio_features, kv_cache=self.kv_cache)