def logits()

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)