| { | |
| "architectures": [ | |
| "DacModel" | |
| ], | |
| "codebook_dim": 8, | |
| "codebook_loss_weight": 1.0, | |
| "codebook_size": 1024, | |
| "commitment_loss_weight": 0.25, | |
| "decoder_hidden_size": 1536, | |
| "downsampling_ratios": [ | |
| 2, | |
| 4, | |
| 5, | |
| 8 | |
| ], | |
| "encoder_hidden_size": 64, | |
| "hidden_size": 1024, | |
| "hop_length": 512, | |
| "model_type": "dac", | |
| "n_codebooks": 12, | |
| "quantizer_dropout": 0.0, | |
| "sampling_rate": 16000, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.0.dev0", | |
| "upsampling_ratios": [ | |
| 8, | |
| 5, | |
| 4, | |
| 2 | |
| ] | |
| } | |