(diff-svc) D:\AI_Assistant\Proejct>python preprocessing/binarize.py --config training/config_nsf.yaml

| Hparams chains:  ['training/config_nsf.yaml']

| Hparams:

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/Yuuka, 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: 40000, 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: 10, 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/test, ref_norm_layer: bn,

rel_pos: True, reset_phone_dict: True, residual_channels: 384, 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: Yuuka, spec_max: [0.0], spec_min: [-5.0],

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_amp: True, 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, validate: False,

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: ,

| Binarizer:  <class 'preprocessing.SVCpre.SVCBinarizer'>

spkers:  {'Yuuka'}

| spk_map:  {'Yuuka': 0}

Traceback (most recent call last):

  File "D:\AI_Assistant\Proejct\preprocessing\binarize.py", line 22, in <module>

    binarize()

  File "D:\AI_Assistant\Proejct\preprocessing\binarize.py", line 17, in binarize

    binarizer_cls().process()

  File "D:\AI_Assistant\Proejct\preprocessing\base_binarizer.py", line 134, in process

    self.phone_encoder =self._phone_encoder()

  File "D:\AI_Assistant\Proejct\preprocessing\SVCpre.py", line 63, in _phone_encoder

    return Hubertencoder(hparams['hubert_path'])

  File "D:\AI_Assistant\Proejct\preprocessing\hubertinfer.py", line 28, in __init__

    self.hbt_model = hubert_soft(str(pt_path)).to(self.dev)

  File "D:\AI_Assistant\Proejct\network\hubert\hubert_model.py", line 227, in hubert_soft

    checkpoint = torch.load(path)

  File "D:\Users\lamer\anaconda3\envs\diff-svc\lib\site-packages\torch\serialization.py", line 795, in load

    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)

  File "D:\Users\lamer\anaconda3\envs\diff-svc\lib\site-packages\torch\serialization.py", line 1002, in _legacy_load

    magic_number = pickle_module.load(f, **pickle_load_args)

EOFError: Ran out of input

이런 오류가 발생했는데

모듈 버전이나 파일 경로, 파일 이름의 특수기호 제거 등을 해봤으나 해결되지 않았습니다.

혹시 해결방법 아시면 알려주시면 감사드리겠습니다 ㅠ