| general: | |
| dataset_path: $npy_dataset_path | |
| cpu: True | |
| model_type: S2UT | |
| dataset_size: 5 | |
| dump_speech_waveforms_dir: $dump_waveforms_dir_path | |
| stage1: | |
| data: $data_bin | |
| task: speech_to_speech | |
| path: $checkpoint | |
| config_yaml: config.yaml | |
| max_len_b: 100000 | |
| beam: 10 | |
| target_is_code: True | |
| max_target_positions: 3000 | |
| target_code_size: 100 | |
| stage2: | |
| vocoder: $vocoder_path | |
| vocoder_cfg: $vocoder_cfg_json | |
| dur_prediction: True | |