Method _embed_audio

models.py:190–191

(self, codebook: int, tokens: torch.Tensor)

        self.decoder.reset_caches()

    def _embed_audio(self, codebook: int, tokens: torch.Tensor) -> torch.Tensor:
        return self.audio_embeddings(tokens + codebook * self.config.audio_vocab_size)

    def _embed_tokens(self, tokens: torch.Tensor) -> torch.Tensor:
        text_embeds = self.text_embeddings(tokens[:, :, -1]).unsqueeze(-2)