| { | |
| "model_type": "sensevoice", | |
| "vocab_size": 25055, | |
| "input_size": 560, | |
| "encoder_conf": { | |
| "output_size": 512, | |
| "attention_heads": 4, | |
| "linear_units": 2048, | |
| "num_blocks": 50, | |
| "tp_blocks": 20, | |
| "dropout_rate": 0.1, | |
| "attention_dropout_rate": 0.1, | |
| "kernel_size": 11, | |
| "sanm_shift": 0, | |
| "normalize_before": true | |
| }, | |
| "frontend_conf": { | |
| "fs": 16000, | |
| "window": "hamming", | |
| "n_mels": 80, | |
| "frame_length": 25, | |
| "frame_shift": 10, | |
| "lfr_m": 7, | |
| "lfr_n": 6 | |
| } | |
| } |