Spaces:
Sleeping
Sleeping
| K_step: 1000 | |
| accumulate_grad_batches: 1 | |
| audio_num_mel_bins: 128 | |
| audio_sample_rate: 44100 | |
| 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/Unnamed | |
| check_val_every_n_epoch: 10 | |
| choose_test_manually: false | |
| clip_grad_norm: 1 | |
| config_path: training/config_nsf.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: 60000 | |
| 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: 40.0 | |
| ffn_act: gelu | |
| ffn_padding: SAME | |
| fft_size: 2048 | |
| fmax: 16000 | |
| fmin: 40 | |
| fs2_ckpt: '' | |
| gaussian_start: true | |
| gen_dir_name: '' | |
| gen_tgt_spk_id: -1 | |
| hidden_size: 256 | |
| hop_size: 512 | |
| hubert_gpu: true | |
| hubert_path: checkpoints/hubert/hubert_soft.pt | |
| infer: false | |
| keep_bins: 128 | |
| 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: 0.0008 | |
| max_beta: 0.02 | |
| max_epochs: 3000 | |
| max_eval_sentences: 1 | |
| max_eval_tokens: 60000 | |
| max_frames: 42000 | |
| max_input_tokens: 60000 | |
| max_sentences: 14 | |
| 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 | |
| no_fs2: true | |
| 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: '' | |
| processed_data_dir: xxx | |
| profile_infer: false | |
| raw_data_dir: data/raw/Unnamed | |
| ref_norm_layer: bn | |
| rel_pos: true | |
| reset_phone_dict: true | |
| residual_channels: 384 | |
| residual_layers: 20 | |
| save_best: true | |
| 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: Unnamed | |
| spec_max: | |
| - 0.47615352272987366 | |
| - 0.6125704050064087 | |
| - 0.7518845796585083 | |
| - 0.900716245174408 | |
| - 0.8935521841049194 | |
| - 0.9057011604309082 | |
| - 0.9648348689079285 | |
| - 0.9044283032417297 | |
| - 0.9109272360801697 | |
| - 0.9744535088539124 | |
| - 0.9476388692855835 | |
| - 0.9883336424827576 | |
| - 1.0821290016174316 | |
| - 1.046391248703003 | |
| - 0.9829667806625366 | |
| - 1.0163493156433105 | |
| - 0.9825412631034851 | |
| - 1.0021960735321045 | |
| - 1.052114725112915 | |
| - 1.128888726234436 | |
| - 1.186057209968567 | |
| - 1.112004280090332 | |
| - 1.1282787322998047 | |
| - 1.051572322845459 | |
| - 1.1104764938354492 | |
| - 1.176831603050232 | |
| - 1.13348388671875 | |
| - 1.1075258255004883 | |
| - 1.1696264743804932 | |
| - 1.0231049060821533 | |
| - 0.9303848743438721 | |
| - 1.1257890462875366 | |
| - 1.1610286235809326 | |
| - 1.0335885286331177 | |
| - 1.0645352602005005 | |
| - 1.0619306564331055 | |
| - 1.1310148239135742 | |
| - 1.1191954612731934 | |
| - 1.1307402849197388 | |
| - 1.2094721794128418 | |
| - 1.2683185338974 | |
| - 1.1212272644042969 | |
| - 1.1781182289123535 | |
| - 1.1501952409744263 | |
| - 0.9884514808654785 | |
| - 0.9226155281066895 | |
| - 0.9469702839851379 | |
| - 1.023751139640808 | |
| - 1.1348609924316406 | |
| - 1.087107539176941 | |
| - 0.9899962544441223 | |
| - 1.061837077140808 | |
| - 1.0341650247573853 | |
| - 0.9019684195518494 | |
| - 0.7986546158790588 | |
| - 0.7983465194702148 | |
| - 0.7755436301231384 | |
| - 0.701917290687561 | |
| - 0.7639197707176208 | |
| - 0.7503461837768555 | |
| - 0.6701087951660156 | |
| - 0.5326520800590515 | |
| - 0.6320568323135376 | |
| - 0.4748716950416565 | |
| - 0.41016310453414917 | |
| - 0.4754445552825928 | |
| - 0.4267503023147583 | |
| - 0.391481876373291 | |
| - 0.3118276298046112 | |
| - 0.3193877339363098 | |
| - 0.3111794888973236 | |
| - 0.3342774212360382 | |
| - 0.1353837102651596 | |
| - 0.16596835851669312 | |
| - 0.1730986088514328 | |
| - 0.2325316220521927 | |
| - 0.17107760906219482 | |
| - 0.10877621918916702 | |
| - 0.2612082064151764 | |
| - 0.11200784891843796 | |
| - 0.14075303077697754 | |
| - 0.07312829792499542 | |
| - -0.011712555773556232 | |
| - 0.1741427332162857 | |
| - 0.19782507419586182 | |
| - 0.03305494412779808 | |
| - 0.004054426681250334 | |
| - 0.1011907309293747 | |
| - 0.1317272037267685 | |
| - 0.014256341382861137 | |
| - 0.019952761009335518 | |
| - -0.1253873109817505 | |
| - -0.14854255318641663 | |
| - -0.14063480496406555 | |
| - -0.1331133395433426 | |
| - -0.28339776396751404 | |
| - -0.38559386134147644 | |
| - -0.2798943519592285 | |
| - -0.19351321458816528 | |
| - -0.23238061368465424 | |
| - -0.2850213944911957 | |
| - -0.20320385694503784 | |
| - -0.24087588489055634 | |
| - -0.15823237597942352 | |
| - -0.13949760794639587 | |
| - -0.19627133011817932 | |
| - -0.1920071393251419 | |
| - -0.19384469091892242 | |
| - -0.22403620183467865 | |
| - -0.18197931349277496 | |
| - -0.28423866629600525 | |
| - -0.26859334111213684 | |
| - -0.3213472068309784 | |
| - -0.3303631842136383 | |
| - -0.3835512697696686 | |
| - -0.3256210386753082 | |
| - -0.3938714265823364 | |
| - -0.4373253881931305 | |
| - -0.4146285951137543 | |
| - -0.4861420691013336 | |
| - -0.4018196761608124 | |
| - -0.46770456433296204 | |
| - -0.4100344479084015 | |
| - -0.5364681482315063 | |
| - -0.5802102088928223 | |
| - -0.5856970548629761 | |
| - -0.47378262877464294 | |
| - -0.36258620023727417 | |
| spec_min: | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| - -4.999994277954102 | |
| 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: false | |
| 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: 1000 | |
| valid_num: 0 | |
| valid_set_name: valid | |
| vocoder: network.vocoders.nsf_hifigan.NsfHifiGAN | |
| vocoder_ckpt: checkpoints/nsf_hifigan/model | |
| warmup_updates: 2000 | |
| wav2spec_eps: 1e-6 | |
| weight_decay: 0 | |
| win_size: 2048 | |
| work_dir: checkpoints/Unnamed | |