| data_root: N/A | |
| input_channels: 1 | |
| input_feat_per_channel: 80 | |
| multitask: | |
| source_unit: | |
| data: N/A | |
| decoder_type: transformer | |
| dict: N/A | |
| encoder_layer: 6 | |
| loss_weight: 8.0 | |
| target_type: text | |
| output_channels: 1 | |
| output_feat_per_channel: 1 | |
| output_feat_reduction_rate: 0 | |
| output_sample_rate: 16000 | |
| specaugment: | |
| freq_mask_F: 27 | |
| freq_mask_N: 1 | |
| time_mask_N: 1 | |
| time_mask_T: 100 | |
| time_mask_p: 1.0 | |
| time_wrap_W: 0 | |
| transforms: | |
| _eval: | |
| - utterance_cmvn | |
| _train: | |
| - utterance_cmvn | |
| - specaugment | |
| vocoder: | |
| dur_prediction: true | |
| model_path: N/A | |
| speaker: false | |
| type: code_hifigan | |