add .gitattributes

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_ckpt_steps* filter=lfs diff=lfs merge=lfs -text

checkpoints/.gitattributes

@@ -0,0 +1 @@
+model_ckpt_steps* filter=lfs diff=lfs merge=lfs -text

checkpoints/0102_xiaoma_pe/config.yaml

@@ -0,0 +1,172 @@
+accumulate_grad_batches: 1
+audio_num_mel_bins: 80
+audio_sample_rate: 24000
+base_config:
+- configs/tts/lj/fs2.yaml
+binarization_args:
+  shuffle: false
+  with_align: true
+  with_f0: true
+  with_f0cwt: true
+  with_spk_embed: true
+  with_txt: true
+  with_wav: false
+binarizer_cls: data_gen.tts.base_binarizer.BaseBinarizer
+binary_data_dir: data/binary/xiaoma1022_24k_128hop
+check_val_every_n_epoch: 10
+clip_grad_norm: 1
+cwt_add_f0_loss: false
+cwt_hidden_size: 128
+cwt_layers: 2
+cwt_loss: l1
+cwt_std_scale: 0.8
+debug: false
+dec_ffn_kernel_size: 9
+dec_layers: 4
+decoder_type: fft
+dict_dir: ''
+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: 2
+enc_ffn_kernel_size: 9
+enc_layers: 4
+encoder_K: 8
+encoder_type: fft
+endless_ds: true
+ffn_act: gelu
+ffn_padding: SAME
+fft_size: 512
+fmax: 12000
+fmin: 30
+gen_dir_name: ''
+hidden_size: 256
+hop_size: 128
+infer: false
+lambda_commit: 0.25
+lambda_energy: 0.1
+lambda_f0: 1.0
+lambda_ph_dur: 1.0
+lambda_sent_dur: 1.0
+lambda_uv: 1.0
+lambda_word_dur: 1.0
+load_ckpt: ''
+log_interval: 100
+loud_norm: false
+lr: 2.0
+max_epochs: 1000
+max_eval_sentences: 1
+max_eval_tokens: 60000
+max_frames: 5000
+max_input_tokens: 1550
+max_sentences: 100000
+max_tokens: 20000
+max_updates: 60000
+mel_loss: l1
+mel_vmax: 1.5
+mel_vmin: -6
+min_level_db: -120
+norm_type: gn
+num_ckpt_keep: 3
+num_heads: 2
+num_sanity_val_steps: 5
+num_spk: 1
+num_test_samples: 20
+num_valid_plots: 10
+optimizer_adam_beta1: 0.9
+optimizer_adam_beta2: 0.98
+out_wav_norm: false
+pitch_ar: false
+pitch_enc_hidden_stride_kernel:
+- 0,2,5
+- 0,2,5
+- 0,2,5
+pitch_extractor_conv_layers: 2
+pitch_loss: l1
+pitch_norm: log
+pitch_type: frame
+pre_align_args:
+  allow_no_txt: false
+  denoise: false
+  forced_align: mfa
+  txt_processor: en
+  use_sox: false
+  use_tone: true
+pre_align_cls: data_gen.tts.lj.pre_align.LJPreAlign
+predictor_dropout: 0.5
+predictor_grad: 0.1
+predictor_hidden: -1
+predictor_kernel: 5
+predictor_layers: 2
+prenet_dropout: 0.5
+prenet_hidden_size: 256
+pretrain_fs_ckpt: ''
+processed_data_dir: data/processed/ljspeech
+profile_infer: false
+raw_data_dir: data/raw/LJSpeech-1.1
+ref_norm_layer: bn
+reset_phone_dict: true
+save_best: false
+save_ckpt: true
+save_codes:
+- configs
+- modules
+- tasks
+- utils
+- usr
+save_f0: false
+save_gt: false
+seed: 1234
+sort_by_len: true
+stop_token_weight: 5.0
+task_cls: tasks.tts.pe.PitchExtractionTask
+test_ids:
+- 68
+- 70
+- 74
+- 87
+- 110
+- 172
+- 190
+- 215
+- 231
+- 294
+- 316
+- 324
+- 402
+- 422
+- 485
+- 500
+- 505
+- 508
+- 509
+- 519
+test_input_dir: ''
+test_num: 523
+test_set_name: test
+train_set_name: train
+use_denoise: false
+use_energy_embed: false
+use_gt_dur: false
+use_gt_f0: false
+use_pitch_embed: true
+use_pos_embed: true
+use_spk_embed: false
+use_spk_id: false
+use_split_spk_id: false
+use_uv: true
+use_var_enc: false
+val_check_interval: 2000
+valid_num: 348
+valid_set_name: valid
+vocoder: pwg
+vocoder_ckpt: ''
+warmup_updates: 2000
+weight_decay: 0
+win_size: 512
+work_dir: checkpoints/0102_xiaoma_pe

checkpoints/0102_xiaoma_pe/model_ckpt_steps_60000.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53942abd8cb908b6d161e1ad7ff3d7d0dd6b204d5bf050613c9d00c56b185ceb
+size 13047222

checkpoints/0109_hifigan_bigpopcs_hop128/config.yaml

@@ -0,0 +1,241 @@
+accumulate_grad_batches: 1
+adam_b1: 0.8
+adam_b2: 0.99
+amp: false
+audio_num_mel_bins: 80
+audio_sample_rate: 24000
+aux_context_window: 0
+#base_config:
+#- egs/egs_bases/singing/pwg.yaml
+#- egs/egs_bases/tts/vocoder/hifigan.yaml
+binarization_args:
+  reset_phone_dict: true
+  reset_word_dict: true
+  shuffle: false
+  trim_eos_bos: false
+  trim_sil: false
+  with_align: false
+  with_f0: true
+  with_f0cwt: false
+  with_linear: false
+  with_spk_embed: false
+  with_spk_id: true
+  with_txt: false
+  with_wav: true
+  with_word: false
+binarizer_cls: data_gen.tts.singing.binarize.SingingBinarizer
+binary_data_dir: data/binary/big_popcs_24k_hop128
+check_val_every_n_epoch: 10
+clip_grad_norm: 1
+clip_grad_value: 0
+datasets: []
+debug: false
+dec_ffn_kernel_size: 9
+dec_layers: 4
+dict_dir: ''
+disc_start_steps: 40000
+discriminator_grad_norm: 1
+discriminator_optimizer_params:
+  eps: 1.0e-06
+  lr: 0.0002
+  weight_decay: 0.0
+discriminator_params:
+  bias: true
+  conv_channels: 64
+  in_channels: 1
+  kernel_size: 3
+  layers: 10
+  nonlinear_activation: LeakyReLU
+  nonlinear_activation_params:
+    negative_slope: 0.2
+  out_channels: 1
+  use_weight_norm: true
+discriminator_scheduler_params:
+  gamma: 0.999
+  step_size: 600
+dropout: 0.1
+ds_workers: 1
+enc_ffn_kernel_size: 9
+enc_layers: 4
+endless_ds: true
+ffn_act: gelu
+ffn_padding: SAME
+fft_size: 512
+fmax: 12000
+fmin: 30
+frames_multiple: 1
+gen_dir_name: ''
+generator_grad_norm: 10
+generator_optimizer_params:
+  eps: 1.0e-06
+  lr: 0.0002
+  weight_decay: 0.0
+generator_params:
+  aux_channels: 80
+  dropout: 0.0
+  gate_channels: 128
+  in_channels: 1
+  kernel_size: 3
+  layers: 30
+  out_channels: 1
+  residual_channels: 64
+  skip_channels: 64
+  stacks: 3
+  upsample_net: ConvInUpsampleNetwork
+  upsample_params:
+    upsample_scales:
+    - 2
+    - 4
+    - 4
+    - 4
+  use_nsf: false
+  use_pitch_embed: true
+  use_weight_norm: true
+generator_scheduler_params:
+  gamma: 0.999
+  step_size: 600
+griffin_lim_iters: 60
+hidden_size: 256
+hop_size: 128
+infer: false
+lambda_adv: 1.0
+lambda_cdisc: 4.0
+lambda_energy: 0.0
+lambda_f0: 0.0
+lambda_mel: 5.0
+lambda_mel_adv: 1.0
+lambda_ph_dur: 0.0
+lambda_sent_dur: 0.0
+lambda_uv: 0.0
+lambda_word_dur: 0.0
+load_ckpt: ''
+loud_norm: false
+lr: 2.0
+max_epochs: 1000
+max_frames: 2400
+max_input_tokens: 1550
+max_samples: 8192
+max_sentences: 20
+max_tokens: 24000
+max_updates: 3000000
+max_valid_sentences: 1
+max_valid_tokens: 60000
+mel_loss: ssim:0.5|l1:0.5
+mel_vmax: 1.5
+mel_vmin: -6
+min_frames: 0
+min_level_db: -120
+num_ckpt_keep: 3
+num_heads: 2
+num_mels: 80
+num_sanity_val_steps: 5
+num_spk: 100
+num_test_samples: 0
+num_valid_plots: 10
+optimizer_adam_beta1: 0.9
+optimizer_adam_beta2: 0.98
+out_wav_norm: false
+pitch_extractor: parselmouth
+pitch_type: frame
+pre_align_args:
+  allow_no_txt: false
+  denoise: false
+  sox_resample: true
+  sox_to_wav: false
+  trim_sil: false
+  txt_processor: zh
+  use_tone: false
+pre_align_cls: data_gen.tts.singing.pre_align.SingingPreAlign
+predictor_grad: 0.0
+print_nan_grads: false
+processed_data_dir: ''
+profile_infer: false
+raw_data_dir: ''
+ref_level_db: 20
+rename_tmux: true
+rerun_gen: true
+resblock: '1'
+resblock_dilation_sizes:
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+- - 1
+  - 3
+  - 5
+resblock_kernel_sizes:
+- 3
+- 7
+- 11
+resume_from_checkpoint: 0
+save_best: true
+save_codes: []
+save_f0: true
+save_gt: true
+scheduler: rsqrt
+seed: 1234
+sort_by_len: true
+stft_loss_params:
+  fft_sizes:
+  - 1024
+  - 2048
+  - 512
+  hop_sizes:
+  - 120
+  - 240
+  - 50
+  win_lengths:
+  - 600
+  - 1200
+  - 240
+  window: hann_window
+task_cls: tasks.vocoder.hifigan.HifiGanTask
+tb_log_interval: 100
+test_ids: []
+test_input_dir: ''
+test_num: 50
+test_prefixes: []
+test_set_name: test
+train_set_name: train
+train_sets: ''
+upsample_initial_channel: 512
+upsample_kernel_sizes:
+- 16
+- 16
+- 4
+- 4
+upsample_rates:
+- 8
+- 4
+- 2
+- 2
+use_cdisc: false
+use_cond_disc: false
+use_fm_loss: false
+use_gt_dur: true
+use_gt_f0: true
+use_mel_loss: true
+use_ms_stft: false
+use_pitch_embed: true
+use_ref_enc: true
+use_spec_disc: false
+use_spk_embed: false
+use_spk_id: false
+use_split_spk_id: false
+val_check_interval: 2000
+valid_infer_interval: 10000
+valid_monitor_key: val_loss
+valid_monitor_mode: min
+valid_set_name: valid
+vocoder: pwg
+vocoder_ckpt: ''
+vocoder_denoise_c: 0.0
+warmup_updates: 8000
+weight_decay: 0
+win_length: null
+win_size: 512
+window: hann
+word_size: 3000
+work_dir: checkpoints/0109_hifigan_bigpopcs_hop128

checkpoints/0109_hifigan_bigpopcs_hop128/model_ckpt_steps_1512000.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb68f3ce0c46ba0a8b6d49718f1fffdf5bd7bcab769a986fd2fd129835cc1d1
+size 55827436

checkpoints/0228_opencpop_ds100_rel/config.yaml

@@ -0,0 +1,342 @@
+K_step: 100
+accumulate_grad_batches: 1
+audio_num_mel_bins: 80
+audio_sample_rate: 24000
+base_config:
+- usr/configs/popcs_ds_beta6.yaml
+- usr/configs/midi/cascade/opencs/opencpop_statis.yaml
+binarization_args:
+  shuffle: false
+  with_align: true
+  with_f0: true
+  with_f0cwt: true
+  with_spk_embed: false
+  with_txt: true
+  with_wav: true
+binarizer_cls: data_gen.singing.binarize.OpencpopBinarizer
+binary_data_dir: data/binary/opencpop-midi-dp
+check_val_every_n_epoch: 10
+clip_grad_norm: 1
+content_cond_steps: []
+cwt_add_f0_loss: false
+cwt_hidden_size: 128
+cwt_layers: 2
+cwt_loss: l1
+cwt_std_scale: 0.8
+datasets:
+- popcs
+debug: false
+dec_ffn_kernel_size: 9
+dec_layers: 4
+decay_steps: 50000
+decoder_type: fft
+dict_dir: ''
+diff_decoder_type: wavenet
+diff_loss_type: l1
+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: true
+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
+infer: false
+keep_bins: 80
+lambda_commit: 0.25
+lambda_energy: 0.0
+lambda_f0: 0.0
+lambda_ph_dur: 1.0
+lambda_sent_dur: 1.0
+lambda_uv: 0.0
+lambda_word_dur: 1.0
+load_ckpt: ''
+log_interval: 100
+loud_norm: false
+lr: 0.001
+max_beta: 0.06
+max_epochs: 1000
+max_eval_sentences: 1
+max_eval_tokens: 60000
+max_frames: 8000
+max_input_tokens: 1550
+max_sentences: 48
+max_tokens: 40000
+max_updates: 160000
+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: 3
+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
+pe_enable: true
+pitch_ar: false
+pitch_enc_hidden_stride_kernel:
+- 0,2,5
+- 0,2,5
+- 0,2,5
+pitch_extractor: parselmouth
+pitch_loss: l1
+pitch_norm: log
+pitch_type: frame
+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: data/processed/popcs
+profile_infer: false
+raw_data_dir: data/raw/popcs
+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
+- tasks
+- utils
+- usr
+save_f0: true
+save_gt: false
+schedule_type: linear
+seed: 1234
+sort_by_len: true
+spec_max:
+- -0.79453
+- -0.81116
+- -0.61631
+- -0.30679
+- -0.13863
+- -0.050652
+- -0.11563
+- -0.10679
+- -0.091068
+- -0.062174
+- -0.075302
+- -0.072217
+- -0.063815
+- -0.073299
+- 0.007361
+- -0.072508
+- -0.050234
+- -0.16534
+- -0.26928
+- -0.20782
+- -0.20823
+- -0.11702
+- -0.070128
+- -0.065868
+- -0.012675
+- 0.0015121
+- -0.089902
+- -0.21392
+- -0.23789
+- -0.28922
+- -0.30405
+- -0.23029
+- -0.22088
+- -0.21542
+- -0.29367
+- -0.30137
+- -0.38281
+- -0.4359
+- -0.28681
+- -0.46855
+- -0.57485
+- -0.47022
+- -0.54266
+- -0.44848
+- -0.6412
+- -0.687
+- -0.6486
+- -0.76436
+- -0.49971
+- -0.71068
+- -0.69724
+- -0.61487
+- -0.55843
+- -0.69773
+- -0.57502
+- -0.70919
+- -0.82431
+- -0.84213
+- -0.90431
+- -0.8284
+- -0.77945
+- -0.82758
+- -0.87699
+- -1.0532
+- -1.0766
+- -1.1198
+- -1.0185
+- -0.98983
+- -1.0001
+- -1.0756
+- -1.0024
+- -1.0304
+- -1.0579
+- -1.0188
+- -1.05
+- -1.0842
+- -1.0923
+- -1.1223
+- -1.2381
+- -1.6467
+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
+- -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
+spk_cond_steps: []
+stop_token_weight: 5.0
+task_cls: usr.diffsinger_task.DiffSingerMIDITask
+test_ids: []
+test_input_dir: ''
+test_num: 0
+test_prefixes:
+- "popcs-\u8BF4\u6563\u5C31\u6563"
+- "popcs-\u9690\u5F62\u7684\u7FC5\u8180"
+test_set_name: test
+timesteps: 100
+train_set_name: train
+use_denoise: false
+use_energy_embed: false
+use_gt_dur: false
+use_gt_f0: false
+use_midi: true
+use_nsf: true
+use_pitch_embed: false
+use_pos_embed: true
+use_spk_embed: false
+use_spk_id: false
+use_split_spk_id: false
+use_uv: true
+use_var_enc: false
+val_check_interval: 2000
+valid_num: 0
+valid_set_name: valid
+vocoder: 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/0228_opencpop_ds100_rel

checkpoints/0228_opencpop_ds100_rel/model_ckpt_steps_160000.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8261f7415bb39eb80a19d4c27c0ea084f63af2fdf6b82e63fcbd9cd82fc90c
+size 170226367

checkpoints/clean.py

@@ -0,0 +1,12 @@
+import sys
+import torch
+
+if __name__ == '__main__':
+    ckpt_path = sys.argv[1]
+    checkpoint = torch.load(ckpt_path, map_location='cpu')
+    print(checkpoint['state_dict'].keys())
+    if 'model' in checkpoint['state_dict']:
+        checkpoint = {'state_dict': {'model': checkpoint['state_dict']['model']}}
+    else:
+        checkpoint = {'state_dict': {'model_gen': checkpoint['state_dict']['model_gen']}}
+    torch.save(checkpoint, ckpt_path, _use_new_zipfile_serialization=False)

checkpoints/cleaner.py

@@ -0,0 +1,8 @@
+import sys
+import torch
+
+if __name__ == '__main__':
+    ckpt_path = sys.argv[1]
+    checkpoint = torch.load(ckpt_path, map_location='cpu')
+    checkpoint = {'state_dict': checkpoint['state_dict']}
+    torch.save(checkpoint, ckpt_path, _use_new_zipfile_serialization=False)