| frontend: wav_frontend | |
| frontend_conf: | |
| fs: 16000 | |
| window: hamming | |
| n_mels: 80 | |
| frame_length: 25 | |
| frame_shift: 10 | |
| lfr_m: 7 | |
| lfr_n: 6 | |
| model: paraformer | |
| model_conf: | |
| ctc_weight: 0.0 | |
| lsm_weight: 0.1 | |
| length_normalized_loss: true | |
| predictor_weight: 1.0 | |
| predictor_bias: 1 | |
| sampling_ratio: 0.75 | |
| preencoder: null | |
| preencoder_conf: {} | |
| encoder: sanm | |
| encoder_conf: | |
| output_size: 512 | |
| attention_heads: 4 | |
| linear_units: 2048 | |
| num_blocks: 50 | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.1 | |
| attention_dropout_rate: 0.1 | |
| input_layer: pe | |
| pos_enc_class: SinusoidalPositionEncoder | |
| normalize_before: true | |
| kernel_size: 11 | |
| sanm_shfit: 0 | |
| selfattention_layer_type: sanm | |
| postencoder: null | |
| postencoder_conf: {} | |
| decoder: paraformer_decoder_sanm | |
| decoder_conf: | |
| attention_heads: 4 | |
| linear_units: 2048 | |
| num_blocks: 16 | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.1 | |
| self_attention_dropout_rate: 0.1 | |
| src_attention_dropout_rate: 0.1 | |
| att_layer_num: 16 | |
| kernel_size: 11 | |
| sanm_shfit: 0 | |
| predictor: cif_predictor_v2 | |
| predictor_conf: | |
| idim: 512 | |
| threshold: 1.0 | |
| l_order: 1 | |
| r_order: 1 | |
| tail_threshold: 0.45 | |
| version: '202211' | |