| { |
| "model_type": "pocket_tts", |
| "flow_lm": { |
| "dtype": "float32", |
| "flow": { |
| "dim": 512, |
| "depth": 6 |
| }, |
| "transformer": { |
| "hidden_scale": 4, |
| "max_period": 10000, |
| "d_model": 1024, |
| "num_heads": 16, |
| "num_layers": 6 |
| }, |
| "lookup_table": { |
| "dim": 1024, |
| "n_bins": 4000, |
| "tokenizer": "sentencepiece", |
| "tokenizer_path": "hf://kyutai/pocket-tts-without-voice-cloning/tokenizer.model@d4fdd22ae8c8e1cb3634e150ebeff1dab2d16df3" |
| }, |
| "weights_path": null |
| }, |
| "mimi": { |
| "dtype": "float32", |
| "sample_rate": 24000, |
| "channels": 1, |
| "frame_rate": 12.5, |
| "seanet": { |
| "dimension": 512, |
| "channels": 1, |
| "n_filters": 64, |
| "n_residual_layers": 1, |
| "ratios": [ |
| 6, |
| 5, |
| 4 |
| ], |
| "kernel_size": 7, |
| "residual_kernel_size": 3, |
| "last_kernel_size": 3, |
| "dilation_base": 2, |
| "pad_mode": "constant", |
| "compress": 2 |
| }, |
| "transformer": { |
| "d_model": 512, |
| "input_dimension": 512, |
| "output_dimensions": [ |
| 512 |
| ], |
| "num_heads": 8, |
| "num_layers": 2, |
| "layer_scale": 0.01, |
| "context": 250, |
| "dim_feedforward": 2048, |
| "max_period": 10000.0 |
| }, |
| "quantizer": { |
| "dimension": 32, |
| "output_dimension": 512 |
| }, |
| "weights_path": null |
| }, |
| "weights_path": "hf://kyutai/pocket-tts/tts_b6369a24.safetensors@427e3d61b276ed69fdd03de0d185fa8a8d97fc5b", |
| "weights_path_without_voice_cloning": "hf://kyutai/pocket-tts-without-voice-cloning/tts_b6369a24.safetensors@d4fdd22ae8c8e1cb3634e150ebeff1dab2d16df3", |
| "model_path": null |
| } |