{ "transformers_version": "5.19.0.dev0", "architectures": [ "LiquidCodecModel" ], "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "encoder_dim": 512, "encoder_conv_dim": 256, "stft_n_fft": 1280, "stft_hop_length": 320, "stft_win_length": 1280, "stft_frame_stack": 6, "quantizer_dim": 256, "fsq_levels": [ 8, 7, 6, 6 ], "n_q": 12, "decoder_window": 30, "sampling_rate": 24000, "initializer_range": 0.02, "model_type": "liquid_codec", "output_attentions": false, "sample_rate": 24000, "frame_samples": 1920, "auto_map": { "AutoConfig": "configuration_liquid_codec.LiquidCodecConfig", "AutoModel": "modeling_liquid_codec.LiquidCodecModel" }, "decoder_config": { "attention_bias": false, "attention_dropout": 0.0, "conv_L_cache": 7, "conv_bias": false, "frame_stack": 6, "head_dim": 64, "hidden_size": 512, "hop_length": 320, "initializer_range": 0.02, "intermediate_size": 2304, "layer_types": [ "conv", "conv", "sliding_attention", "conv", "sliding_attention", "conv", "sliding_attention", "conv" ], "max_position_embeddings": 131072, "model_type": "liquid_codec_decoder", "n_fft": 1280, "norm_eps": 1e-05, "num_attention_heads": 8, "num_hidden_layers": 8, "num_key_value_heads": 2, "quantization_dim": 256, "rope_parameters": { "sliding_attention": { "partial_rotary_factor": 1.0, "rope_theta": 1000000.0, "rope_type": "default" } }, "sliding_window": 30, "use_attention_gate": true, "use_cache": false, "use_sandwich_norm": true, "win_length": 1280 }, "encoder_config": { "attention_bias": false, "attention_dropout": 0.0, "conv_L_cache": 7, "conv_bias": false, "embedder_hidden_act": "silu", "embedder_hidden_size": 256, "frame_stack": 6, "head_dim": 64, "hidden_size": 512, "initializer_range": 0.02, "intermediate_size": 2304, "layer_types": [ "conv", "conv", "full_attention", "conv", "full_attention", "conv", "full_attention", "conv" ], "max_position_embeddings": 131072, "model_type": "liquid_codec_encoder", "n_fft": 1280, "norm_eps": 1e-05, "num_attention_heads": 8, "num_hidden_layers": 8, "num_key_value_heads": 2, "quantization_dim": 256, "rope_parameters": { "full_attention": { "partial_rotary_factor": 1.0, "rope_theta": 1000000.0, "rope_type": "default" } }, "sliding_window": null, "use_attention_gate": true, "use_cache": false, "use_sandwich_norm": true }, "num_quantizers": 12, "quantization_dim": 256, "quantization_levels": [ 8, 7, 6, 6 ] }