Spaces:
Runtime error
Runtime error
| { | |
| "base_config": "config/vitssvc.json", | |
| "model_type": "VitsSVC", | |
| "dataset": [ | |
| "m4singer", | |
| "opencpop", | |
| "opensinger", | |
| "svcc", | |
| "vctk" | |
| ], | |
| "dataset_path": { | |
| // TODO: Fill in your dataset path | |
| "m4singer": "[M4Singer dataset path]", | |
| "opencpop": "[Opencpop dataset path]", | |
| "opensinger": "[OpenSinger dataset path]", | |
| "svcc": "[SVCC dataset path]", | |
| "vctk": "[VCTK dataset path]" | |
| }, | |
| // TODO: Fill in the output log path. The default value is "Amphion/ckpts/svc" | |
| "log_dir": "ckpts/svc", | |
| "preprocess": { | |
| // TODO: Fill in the output data path. The default value is "Amphion/data" | |
| "processed_dir": "data", | |
| "f0_min": 50, | |
| "f0_max": 1100, | |
| // f0_bin in sovits | |
| "pitch_bin": 256, | |
| // filter_length in sovits | |
| "n_fft": 2048, | |
| // hop_length in sovits | |
| "hop_size": 512, | |
| // win_length in sovits | |
| "win_size": 2048, | |
| "segment_size": 8192, | |
| "n_mel": 100, | |
| "sample_rate": 44100, | |
| // Config for features extraction | |
| "extract_mel": true, | |
| "extract_pitch": true, | |
| "pitch_extractor": "parselmouth", | |
| "extract_energy": false, | |
| "extract_uv": true, | |
| "extract_linear_spec": true, | |
| "extract_audio": true, | |
| // contentvec | |
| "extract_contentvec_feature": true, | |
| "contentvec_sample_rate": 16000, | |
| "contentvec_batch_size": 1, | |
| "contentvec_frameshift": 0.02, | |
| // whisper | |
| "extract_whisper_feature": true, | |
| "whisper_sample_rate": 16000, | |
| "whisper_frameshift": 0.01, | |
| "whisper_downsample_rate": 2, | |
| // Fill in the content-based pretrained model's path | |
| "contentvec_file": "pretrained/contentvec/checkpoint_best_legacy_500.pt", | |
| "wenet_model_path": "pretrained/wenet/20220506_u2pp_conformer_exp/final.pt", | |
| "wenet_config": "pretrained/wenet/20220506_u2pp_conformer_exp/train.yaml", | |
| "whisper_model": "medium", | |
| "whisper_model_path": "pretrained/whisper/medium.pt", | |
| // Config for features usage | |
| "use_mel": true, | |
| "use_frame_pitch": true, | |
| "use_uv": true, | |
| "use_spkid": true, | |
| "use_contentvec": true, | |
| "use_whisper": true, | |
| "use_text": false, | |
| "use_phone": false, | |
| // Extract content features using dataloader | |
| "pin_memory": true, | |
| "num_workers": 8, | |
| "content_feature_batch_size": 16, | |
| // Meta file | |
| "train_file": "train.json", | |
| "valid_file": "test.json", | |
| "spk2id": "singers.json", | |
| "utt2spk": "utt2singer" | |
| }, | |
| "model": { | |
| "condition_encoder": { | |
| // Config for features usage | |
| "merge_mode": "add", | |
| "input_melody_dim": 1, | |
| "use_log_f0": true, | |
| "n_bins_melody": 256, | |
| //# Quantization (0 for not quantization) | |
| "output_melody_dim": 192, | |
| "use_contentvec": true, | |
| "use_whisper": true, | |
| "use_mert": false, | |
| "use_wenet": false, | |
| "whisper_dim": 1024, | |
| "contentvec_dim": 256, | |
| "content_encoder_dim": 192, | |
| "output_singer_dim": 192, | |
| "singer_table_size": 512, | |
| "output_content_dim": 192, | |
| "use_spkid": true, | |
| "pitch_max": 1100.0, | |
| "pitch_min": 50.0, | |
| }, | |
| "vits": { | |
| "inter_channels": 192, | |
| "hidden_channels": 192, | |
| "filter_channels": 256, | |
| "n_heads": 2, | |
| "n_layers": 6, | |
| "kernel_size": 3, | |
| "p_dropout": 0.1, | |
| "ssl_dim": 256, | |
| "n_flow_layer": 4, | |
| "n_layers_q": 3, | |
| "gin_channels": 256, | |
| "n_speakers": 512, | |
| "use_spectral_norm": false, | |
| }, | |
| "generator": "nsfhifigan", | |
| }, | |
| "train": { | |
| "batch_size": 32, | |
| "learning_rate": 2e-4, | |
| "gradient_accumulation_step": 1, | |
| "max_epoch": -1, // -1 means no limit | |
| "save_checkpoint_stride": [ | |
| 3, | |
| 50 | |
| ], | |
| "keep_last": [ | |
| 3, | |
| 2 | |
| ], | |
| "run_eval": [ | |
| true, | |
| true | |
| ], | |
| "adamw": { | |
| "lr": 2.0e-4 | |
| }, | |
| "reducelronplateau": { | |
| "factor": 0.8, | |
| "patience": 30, | |
| "min_lr": 1.0e-4 | |
| }, | |
| "dataloader": { | |
| "num_worker": 8, | |
| "pin_memory": true | |
| }, | |
| "sampler": { | |
| "holistic_shuffle": false, | |
| "drop_last": true | |
| } | |
| }, | |
| "inference": { | |
| "batch_size": 1, | |
| } | |
| } |