K_step: 1000 accumulate_grad_batches: 1 audio_num_mel_bins: 80 audio_sample_rate: 24000 binarization_args: shuffle: false with_align: true with_f0: true with_hubert: true with_spk_embed: false with_wav: false binarizer_cls: preprocessing.SVCpre.SVCBinarizer binary_data_dir: data/binary/atri check_val_every_n_epoch: 10 choose_test_manually: false clip_grad_norm: 1 config_path: training/config.yaml content_cond_steps: [] cwt_add_f0_loss: false cwt_hidden_size: 128 cwt_layers: 2 cwt_loss: l1 cwt_std_scale: 0.8 datasets: - opencpop debug: false dec_ffn_kernel_size: 9 dec_layers: 4 decay_steps: 30000 decoder_type: fft dict_dir: '' diff_decoder_type: wavenet diff_loss_type: l2 dilation_cycle_length: 4 dropout: 0.1 ds_workers: 4 dur_enc_hidden_stride_kernel: - 0,2,3 - 0,2,3 - 0,1,3 dur_loss: mse dur_predictor_kernel: 3 dur_predictor_layers: 5 enc_ffn_kernel_size: 9 enc_layers: 4 encoder_K: 8 encoder_type: fft endless_ds: False f0_bin: 256 f0_max: 1100.0 f0_min: 50.0 ffn_act: gelu ffn_padding: SAME fft_size: 512 fmax: 12000 fmin: 30 fs2_ckpt: '' gaussian_start: true gen_dir_name: '' gen_tgt_spk_id: -1 hidden_size: 256 hop_size: 128 hubert_gpu: true hubert_path: checkpoints/hubert/hubert_soft.pt infer: false keep_bins: 80 lambda_commit: 0.25 lambda_energy: 0.0 lambda_f0: 1.0 lambda_ph_dur: 0.3 lambda_sent_dur: 1.0 lambda_uv: 1.0 lambda_word_dur: 1.0 load_ckpt: '' log_interval: 100 loud_norm: false lr: 5.0e-05 max_beta: 0.02 max_epochs: 3000 max_eval_sentences: 1 max_eval_tokens: 60000 max_frames: 42000 max_input_tokens: 60000 max_sentences: 24 max_tokens: 128000 max_updates: 1000000 mel_loss: ssim:0.5|l1:0.5 mel_vmax: 1.5 mel_vmin: -6.0 min_level_db: -120 norm_type: gn num_ckpt_keep: 10 num_heads: 2 num_sanity_val_steps: 1 num_spk: 1 num_test_samples: 0 num_valid_plots: 10 optimizer_adam_beta1: 0.9 optimizer_adam_beta2: 0.98 out_wav_norm: false pe_ckpt: checkpoints/0102_xiaoma_pe/model_ckpt_steps_60000.ckpt pe_enable: false perform_enhance: true pitch_ar: false pitch_enc_hidden_stride_kernel: - 0,2,5 - 0,2,5 - 0,2,5 pitch_extractor: parselmouth pitch_loss: l2 pitch_norm: log pitch_type: frame pndm_speedup: 10 pre_align_args: allow_no_txt: false denoise: false forced_align: mfa txt_processor: zh_g2pM use_sox: true use_tone: false pre_align_cls: data_gen.singing.pre_align.SingingPreAlign predictor_dropout: 0.5 predictor_grad: 0.1 predictor_hidden: -1 predictor_kernel: 5 predictor_layers: 5 prenet_dropout: 0.5 prenet_hidden_size: 256 pretrain_fs_ckpt: pretrain/nyaru/model_ckpt_steps_60000.ckpt processed_data_dir: xxx profile_infer: false raw_data_dir: data/raw/atri ref_norm_layer: bn rel_pos: true reset_phone_dict: true residual_channels: 256 residual_layers: 20 save_best: false save_ckpt: true save_codes: - configs - modules - src - utils save_f0: true save_gt: false schedule_type: linear seed: 1234 sort_by_len: true speaker_id: atri spec_max: - 0.2987259328365326 - 0.29721200466156006 - 0.23978209495544434 - 0.208412766456604 - 0.25777050852775574 - 0.2514476478099823 - 0.1129382848739624 - 0.03415697440505028 - 0.09860049188137054 - 0.10637332499027252 - 0.13287633657455444 - 0.19744250178337097 - 0.10040587931871414 - 0.13735432922840118 - 0.15107455849647522 - 0.17196381092071533 - 0.08298977464437485 - 0.0632769986987114 - 0.02723858878016472 - -0.001819317927584052 - -0.029565516859292984 - -0.023574354127049446 - -0.01633293740451336 - 0.07143621146678925 - 0.021580500528216362 - 0.07257916033267975 - -0.024349519982933998 - -0.06165708228945732 - -0.10486568510532379 - -0.1363687664270401 - -0.13333871960639954 - -0.13955898582935333 - -0.16613495349884033 - -0.17636367678642273 - -0.2786925733089447 - -0.22967253625392914 - -0.31897130608558655 - -0.18007366359233856 - -0.29366692900657654 - -0.2871025800704956 - -0.36748355627059937 - -0.46071451902389526 - -0.5464922189712524 - -0.5719417333602905 - -0.6020897626876831 - -0.6239874958992004 - -0.5653440952301025 - -0.6508013606071472 - -0.628247857093811 - -0.6809687614440918 - -0.569259762763977 - -0.5423558354377747 - -0.5811785459518433 - -0.5359002351760864 - -0.6565515398979187 - -0.7143737077713013 - -0.8502675890922546 - -0.7979224920272827 - -0.7110578417778015 - -0.763409435749054 - -0.7984790802001953 - -0.6927220821380615 - -0.658117413520813 - -0.7486468553543091 - -0.5949879884719849 - -0.7494576573371887 - -0.7400822639465332 - -0.6822793483734131 - -0.7773582339286804 - -0.661201536655426 - -0.791329026222229 - -0.8982341885566711 - -0.8736728429794312 - -0.7701027393341064 - -0.8490535616874695 - -0.7479292154312134 - -0.9320166110992432 - -1.2862414121627808 - -2.8936190605163574 - -2.924229860305786 spec_min: - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -6.0 - -5.999454021453857 - -5.8822431564331055 - -5.892064571380615 - -5.882402420043945 - -5.786972522735596 - -5.746835231781006 - -5.8594512939453125 - -5.7389445304870605 - -5.718059539794922 - -5.779720306396484 - -5.801984786987305 - -6.0 - -6.0 spk_cond_steps: [] stop_token_weight: 5.0 task_cls: training.task.SVC_task.SVCTask test_ids: [] test_input_dir: '' test_num: 0 test_prefixes: - test test_set_name: test timesteps: 1000 train_set_name: train use_crepe: true use_denoise: false use_energy_embed: false use_gt_dur: false use_gt_f0: false use_midi: false use_nsf: true use_pitch_embed: true use_pos_embed: true use_spk_embed: false use_spk_id: false use_split_spk_id: false use_uv: false use_var_enc: false use_vec: false val_check_interval: 2000 valid_num: 0 valid_set_name: valid vocoder: network.vocoders.hifigan.HifiGAN vocoder_ckpt: checkpoints/0109_hifigan_bigpopcs_hop128 warmup_updates: 2000 wav2spec_eps: 1e-6 weight_decay: 0 win_size: 512 work_dir: checkpoints/atri no_fs2: false