{ "phone_former": "phone_former", "temp_former": "temp_former", "dep_former": "dep_former_csm", "phone_vocab_size": 125, "audio_vocab_size": 2050, "audio_pad_size": 0, "embedding_dim": 1024, "spk_embedding_dim": 192, "num_codebooks": 16, "num_phone_states": 6, "amortization_divisor": 16, "max_look_ahead": 5, "audio_window_size": 625, "phone_window_size": 625 }