Spaces:

Kangarroar
/

ApplioRVC-Inference

Configuration error

App Files Files Community

Kangarroar commited on Dec 30, 2022

Commit

632f309

•

1 Parent(s): ef5bee9

Upload 11 files

Browse files

Files changed (12) hide show

.gitattributes +1 -0
app.py +116 -0
checkpoints/0102_xiaoma_pe/config.yaml +172 -0
checkpoints/0102_xiaoma_pe/model_ckpt_steps_60000.ckpt +3 -0
checkpoints/Unnamed/config.yaml +445 -0
checkpoints/Unnamed/config_nsf.yaml +445 -0
checkpoints/Unnamed/lightning_logs/lastest/hparams.yaml +1 -0
checkpoints/Unnamed/model_ckpt_steps_192000.ckpt +3 -0
checkpoints/nsf_hifigan/NOTICE.txt +74 -0
checkpoints/nsf_hifigan/NOTICE.zh-CN.txt +72 -0
checkpoints/nsf_hifigan/config.json +38 -0
checkpoints/nsf_hifigan/model +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 results/test_output.wav filter=lfs diff=lfs merge=lfs -text
 test_output.wav filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 results/test_output.wav filter=lfs diff=lfs merge=lfs -text
 test_output.wav filter=lfs diff=lfs merge=lfs -text
+checkpoints/nsf_hifigan/model filter=lfs diff=lfs merge=lfs -text

app.py ADDED Viewed

	@@ -0,0 +1,116 @@

+import tkinter as tk
+import tkinter.filedialog
+import tkinter.ttk as ttk
+import tkinter as tk
+from tkinter import ttk
+import wave
+from utils.hparams import hparams
+from preprocessing.data_gen_utils import get_pitch_parselmouth,get_pitch_crepe
+import numpy as np
+import IPython.display as ipd
+import utils
+import librosa
+import torchcrepe
+from infer import *
+import logging
+from infer_tools.infer_tool import *
+from tkinter import Label
+from time import sleep
+import os
+# Create the main window
+window = tk.Tk()
+# Set the window title and size
+window.title("Diff-SVC Rendering Tool")
+window.geometry("250x400")
+# console Textbox
+textbox = tk.Text(window)
+textbox.grid(row=4, column=0, padx=20, pady=20, sticky="nsew")
+loading_animation_label = Label(window)
+loading_animation_label.grid(row=5, column=0)
+# Set the column and row to stretch to fill the available space
+window.grid_columnconfigure(0, weight=1)
+window.grid_rowconfigure(4, weight=1)
+button1 = ttk.Button(window, text="Load Model")
+button1.grid(row=0, column=0, padx=20, pady=20)
+pb = ttk.Progressbar(
+    window,
+    orient='horizontal',
+    mode='indeterminate',
+    length=250
+)
+def start():
+    pb.grid(column=0, row=5, padx=0, pady=0)
+    pb.start(10)
+def stop():
+    pb.stop()
+    pb.grid_remove()
+def button1_clicked():
+    filepath1 = tkinter.filedialog.askopenfilename(title = "Select CKPT File", filetypes=[("Checkpoint files", "*.ckpt")])
+    if filepath1 == '':
+        tkinter.messagebox.showerror("Error", "No CKPT file selected")
+        return
+    filepath2 = tkinter.filedialog.askopenfilename(title = "Select YAML File",filetypes=[("Yaml files", "*.yaml")])
+    if filepath2 == '':
+        tkinter.messagebox.showerror("Error", "No YAML file selected")
+        return
+    model_path = filepath1
+    config_path = filepath2
+    logging.getLogger('numba').setLevel(logging.WARNING)
+    start()
+    # Show a dialog box to input text
+    global project_name
+    project_name = tkinter.simpledialog.askstring("Input", "Enter project name:", parent=window)
+    if project_name == '':
+        tkinter.messagebox.showerror("Error", "No Project Name")
+        return
+    # Use the input text and the value of hubert_gpu as arguments when creating an instance of the Svc class
+    global svc_model
+    hubert_gpu = False
+    svc_model = Svc(project_name, config_path, hubert_gpu, model_path)
+    textbox.insert('end', 'model loaded\n')
+    stop()
+# Assign the callback function to the button's "command" attribute
+button1["command"] = button1_clicked
+button2 = ttk.Button(window, text="Start Rendering")
+button2.grid(row=1, column=0, padx=20, pady=20)
+# Define a callback function for the second button
+def button2_clicked():
+    # Open a file selection dialog for WAV files
+    filepath = tkinter.filedialog.askopenfilename(filetypes=[("WAV files", "*.wav")])
+    # Show a dialog box to input the "key" value
+    key = tkinter.simpledialog.askinteger("Input", "Enter key value:", parent=window)
+    textbox.insert('end', 'Rendering Started, please wait...\n')
+    start()
+    wav_gen = tkinter.simpledialog.askstring("Input", "Enter the track name:", parent=window)
+    if not wav_gen.endswith('.wav'):
+        wav_gen += '.wav'
+    wav_fn = filepath
+    demoaudio, sr = librosa.load(wav_fn)
+    pndm_speedup = 20
+    f0_tst, f0_pred, audio = run_clip(svc_model,file_path=wav_fn, key=key, acc=pndm_speedup, use_crepe=True, use_pe=True, thre=0.05,
+                                        use_gt_mel=False, add_noise_step=500,project_name=project_name,out_path=wav_gen)
+    time.sleep(2)
+    textbox.insert('end', 'Rendering process done!\nPlaying Audio now...')
+    os.startfile(wav_gen)
+    stop()
+button2["command"] = button2_clicked
+#Checkbox
+hubert_gpu = tk.BooleanVar()
+checkbox = tk.Checkbutton(window, text="Use GPU", variable=hubert_gpu)
+checkbox.grid(row=3, column=0)
+# Start the event loop
+window.mainloop()

checkpoints/0102_xiaoma_pe/config.yaml ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1863f12324e43783089ab933edeeb969106b851e30d71019ebbaa9b82099d82a
+size 39141959

checkpoints/Unnamed/config.yaml ADDED Viewed

	@@ -0,0 +1,445 @@

+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: false
+  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: 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: 12
+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: 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: Unnamed
+spec_max:
+- -0.025250941514968872
+- 0.004534448496997356
+- 0.5684943795204163
+- 0.6527385115623474
+- 0.659079372882843
+- 0.7416915893554688
+- 0.844637930393219
+- 0.806076169013977
+- 0.7238750457763672
+- 0.9744535088539124
+- 0.9476388692855835
+- 0.9883336424827576
+- 1.0821290016174316
+- 1.046391248703003
+- 0.9829667806625366
+- 1.0163493156433105
+- 0.9825412631034851
+- 0.9834834337234497
+- 1.052114725112915
+- 1.128888726234436
+- 1.186057209968567
+- 1.112004280090332
+- 1.1282787322998047
+- 1.051572322845459
+- 1.1104764938354492
+- 1.176831603050232
+- 1.13348388671875
+- 0.9916292428970337
+- 0.8383486270904541
+- 0.7735869288444519
+- 0.9303848743438721
+- 1.1257890462875366
+- 1.1610286235809326
+- 1.0335885286331177
+- 1.0645352602005005
+- 1.0619306564331055
+- 1.1310148239135742
+- 1.1191954612731934
+- 1.1307402849197388
+- 1.2094721794128418
+- 1.2683185338974
+- 1.1045044660568237
+- 1.0479614734649658
+- 0.9491603374481201
+- 0.9858523011207581
+- 0.9226155281066895
+- 0.9469702839851379
+- 1.023751139640808
+- 1.1348609924316406
+- 1.087107539176941
+- 0.962234377861023
+- 0.8551340699195862
+- 0.8397778272628784
+- 0.8908605575561523
+- 0.7986546158790588
+- 0.7983465194702148
+- 0.6965265274047852
+- 0.689120352268219
+- 0.6862147450447083
+- 0.5631484985351562
+- 0.48587048053741455
+- 0.5326520800590515
+- 0.4286036193370819
+- 0.35252484679222107
+- 0.3290073573589325
+- 0.4754445552825928
+- 0.3632410168647766
+- 0.391481876373291
+- 0.2200046181678772
+- 0.1869768500328064
+- 0.1539602279663086
+- 0.07932852953672409
+- 0.012834634631872177
+- 0.16596835851669312
+- 0.10024689882993698
+- -0.023952053859829903
+- 0.05635542422533035
+- 0.10877621918916702
+- 0.0382893942296505
+- 0.07318088412284851
+- 0.14075303077697754
+- 0.057870157063007355
+- -0.0520513579249382
+- 0.1741427332162857
+- -0.11154910922050476
+- 0.03305494412779808
+- -0.022758174687623978
+- -0.05313302204012871
+- 0.00024538111756555736
+- -0.26880618929862976
+- -0.0825519785284996
+- -0.3040400445461273
+- -0.44150036573410034
+- -0.36957985162734985
+- -0.438098281621933
+- -0.49879470467567444
+- -0.5903350710868835
+- -0.6418567895889282
+- -0.6425778865814209
+- -0.6178902387619019
+- -0.47356730699539185
+- -0.6052739024162292
+- -0.5359307527542114
+- -0.5759448409080505
+- -0.5498068332672119
+- -0.4661938548088074
+- -0.5811225771903992
+- -0.5229856967926025
+- -0.3902229070663452
+- -0.7037366032600403
+- -0.7260795831680298
+- -0.7540019750595093
+- -0.828707754611969
+- -0.8374698758125305
+- -0.8328713178634644
+- -0.9081047177314758
+- -0.9679695963859558
+- -0.9587443470954895
+- -1.0706337690353394
+- -0.9818469285964966
+- -0.8360191583633423
+- -0.9938982725143433
+- -1.0823708772659302
+- -1.0617167949676514
+- -1.1093820333480835
+- -1.1300138235092163
+- -1.2141350507736206
+- -1.3147293329238892
+spec_min:
+- -4.473258972167969
+- -4.296891689300537
+- -4.390527725219727
+- -4.350704669952393
+- -4.446024417877197
+- -4.3960185050964355
+- -4.164802551269531
+- -4.5063300132751465
+- -4.608232021331787
+- -4.251623630523682
+- -4.4799604415893555
+- -4.733210563659668
+- -4.411860466003418
+- -4.609100818634033
+- -4.726972579956055
+- -4.497627258300781
+- -4.487612247467041
+- -4.665065765380859
+- -4.480506896972656
+- -4.589383125305176
+- -4.86366605758667
+- -4.5183892250061035
+- -4.816161632537842
+- -4.906436443328857
+- -4.897279262542725
+- -4.431278705596924
+- -4.999994277954102
+- -4.871325969696045
+- -4.527368068695068
+- -4.872085094451904
+- -4.894851207733154
+- -4.511948585510254
+- -4.534575939178467
+- -4.57792854309082
+- -4.444681644439697
+- -4.996480464935303
+- -4.74341344833374
+- -4.85427713394165
+- -4.723776817321777
+- -4.7166008949279785
+- -4.749168395996094
+- -4.67240047454834
+- -4.590690612792969
+- -4.576009750366211
+- -4.542308330535889
+- -4.890907287597656
+- -4.631724834442139
+- -4.494126796722412
+- -4.499763488769531
+- -4.574635028839111
+- -4.49362850189209
+- -4.651009559631348
+- -4.684722900390625
+- -4.594520568847656
+- -4.5510125160217285
+- -4.616012096405029
+- -4.561031341552734
+- -4.633460521697998
+- -4.541748046875
+- -4.625052452087402
+- -4.524572372436523
+- -4.563175201416016
+- -4.515830039978027
+- -4.581448554992676
+- -4.556764125823975
+- -4.695038795471191
+- -4.548621654510498
+- -4.5828471183776855
+- -4.750834941864014
+- -4.569651126861572
+- -4.577111721038818
+- -4.549272537231445
+- -4.5840277671813965
+- -4.574136257171631
+- -4.574832439422607
+- -4.549546718597412
+- -4.490700721740723
+- -4.635391712188721
+- -4.567677974700928
+- -4.516189098358154
+- -4.6232805252075195
+- -4.592589855194092
+- -4.593951225280762
+- -4.557478904724121
+- -4.503338813781738
+- -4.512742519378662
+- -4.515079498291016
+- -4.531710147857666
+- -4.5540852546691895
+- -4.441158771514893
+- -4.489132404327393
+- -4.519915580749512
+- -4.570128917694092
+- -4.480836391448975
+- -4.494598865509033
+- -4.51900053024292
+- -4.518474578857422
+- -4.519540309906006
+- -4.495180130004883
+- -4.471179962158203
+- -4.478188514709473
+- -4.475483417510986
+- -4.479583263397217
+- -4.491953372955322
+- -4.4339680671691895
+- -4.469926834106445
+- -4.46633768081665
+- -4.468038082122803
+- -4.489401817321777
+- -4.472512722015381
+- -4.43712043762207
+- -4.469909191131592
+- -4.475585460662842
+- -4.460614204406738
+- -4.4658942222595215
+- -4.4960408210754395
+- -4.499384880065918
+- -4.4431610107421875
+- -4.440634727478027
+- -4.468203544616699
+- -4.461722373962402
+- -4.503596305847168
+- -4.457762241363525
+- -4.453769207000732
+- -4.509873390197754
+- -4.505057334899902
+- -4.486324787139893
+- -4.49452018737793
+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.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

checkpoints/Unnamed/config_nsf.yaml ADDED Viewed

	@@ -0,0 +1,445 @@

+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: 20000
+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: pretrain/nehito_ckpt_steps_1000000.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: 12
+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: 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: Unnamed
+spec_max:
+- -0.4884430170059204
+- 0.004534448496997356
+- 0.5684943795204163
+- 0.6527385115623474
+- 0.659079372882843
+- 0.7416915893554688
+- 0.844637930393219
+- 0.806076169013977
+- 0.7238750457763672
+- 0.9744535088539124
+- 0.9476388692855835
+- 0.9883336424827576
+- 1.0821290016174316
+- 1.046391248703003
+- 0.9829667806625366
+- 1.0163493156433105
+- 0.9825412631034851
+- 0.9834834337234497
+- 0.9811502695083618
+- 1.128888726234436
+- 1.186057209968567
+- 1.112004280090332
+- 1.1282787322998047
+- 1.051572322845459
+- 1.0510444641113281
+- 1.0110565423965454
+- 0.9236567616462708
+- 0.8036720156669617
+- 0.8383486270904541
+- 0.7735869288444519
+- 0.9303848743438721
+- 1.1257890462875366
+- 1.1610286235809326
+- 1.0335885286331177
+- 1.0645352602005005
+- 1.0619306564331055
+- 1.1310148239135742
+- 1.1191954612731934
+- 1.1307402849197388
+- 0.8837698698043823
+- 1.1153966188430786
+- 1.1045044660568237
+- 1.0479614734649658
+- 0.9491603374481201
+- 0.9858523011207581
+- 0.9226155281066895
+- 0.9469702839851379
+- 0.8791896104812622
+- 0.997624933719635
+- 0.9068642854690552
+- 0.9575618505477905
+- 0.8551340699195862
+- 0.8397778272628784
+- 0.8908605575561523
+- 0.7986546158790588
+- 0.7983465194702148
+- 0.6965265274047852
+- 0.640673041343689
+- 0.6690735220909119
+- 0.5631484985351562
+- 0.48587048053741455
+- 0.5326520800590515
+- 0.4286036193370819
+- 0.35252484679222107
+- 0.3290073573589325
+- 0.4754445552825928
+- 0.3632410168647766
+- 0.391481876373291
+- 0.20288512110710144
+- 0.18305960297584534
+- 0.1539602279663086
+- 0.03451670706272125
+- -0.16881510615348816
+- -0.02030198462307453
+- 0.10024689882993698
+- -0.023952053859829903
+- 0.05635542422533035
+- 0.10877621918916702
+- 0.006155031267553568
+- 0.07318088412284851
+- 0.14075303077697754
+- 0.057870157063007355
+- -0.0520513579249382
+- 0.1741427332162857
+- -0.11464552581310272
+- 0.03305494412779808
+- -0.06897418200969696
+- -0.12598733603954315
+- -0.09894973039627075
+- -0.2817802429199219
+- -0.0825519785284996
+- -0.3040400445461273
+- -0.4998124837875366
+- -0.36957985162734985
+- -0.5409602522850037
+- -0.49879470467567444
+- -0.713716983795166
+- -0.6545754671096802
+- -0.6425778865814209
+- -0.6178902387619019
+- -0.47356730699539185
+- -0.6165243983268738
+- -0.5841533541679382
+- -0.5759448409080505
+- -0.5498068332672119
+- -0.4661938548088074
+- -0.5811225771903992
+- -0.614664614200592
+- -0.3902229070663452
+- -0.7037366032600403
+- -0.7260795831680298
+- -0.7540019750595093
+- -0.8360528945922852
+- -0.8374698758125305
+- -0.8328713178634644
+- -0.9081047177314758
+- -0.9679695963859558
+- -0.9587443470954895
+- -1.0706337690353394
+- -0.9818469285964966
+- -0.8360191583633423
+- -0.9938981533050537
+- -1.0823708772659302
+- -1.0617167949676514
+- -1.1093820333480835
+- -1.1300138235092163
+- -1.2141350507736206
+- -1.3147293329238892
+spec_min:
+- -4.473258972167969
+- -4.244492530822754
+- -4.390527725219727
+- -4.209497928619385
+- -4.446024417877197
+- -4.3960185050964355
+- -4.164802551269531
+- -4.5063300132751465
+- -4.608232021331787
+- -4.251623630523682
+- -4.4799604415893555
+- -4.733210563659668
+- -4.411860466003418
+- -4.609100818634033
+- -4.726972579956055
+- -4.428761959075928
+- -4.487612247467041
+- -4.525552749633789
+- -4.480506896972656
+- -4.589383125305176
+- -4.608384132385254
+- -4.385376453399658
+- -4.816161632537842
+- -4.8706955909729
+- -4.848956108093262
+- -4.431278705596924
+- -4.999994277954102
+- -4.818373203277588
+- -4.527368068695068
+- -4.872085094451904
+- -4.894851207733154
+- -4.511948585510254
+- -4.534575939178467
+- -4.57792854309082
+- -4.444681644439697
+- -4.628803253173828
+- -4.74341344833374
+- -4.85427713394165
+- -4.723776817321777
+- -4.7166008949279785
+- -4.749168395996094
+- -4.67240047454834
+- -4.590690612792969
+- -4.576009750366211
+- -4.542308330535889
+- -4.890907287597656
+- -4.613001823425293
+- -4.494126796722412
+- -4.474257946014404
+- -4.574635028839111
+- -4.4817585945129395
+- -4.651009559631348
+- -4.478254795074463
+- -4.523812770843506
+- -4.546536922454834
+- -4.535660266876221
+- -4.470296859741211
+- -4.577486991882324
+- -4.541748046875
+- -4.428532123565674
+- -4.461862564086914
+- -4.489077091217041
+- -4.515830039978027
+- -4.395663738250732
+- -4.439975738525391
+- -4.4290876388549805
+- -4.397741794586182
+- -4.478252410888672
+- -4.399686336517334
+- -4.45617151260376
+- -4.434477806091309
+- -4.442898750305176
+- -4.5840277671813965
+- -4.537542819976807
+- -4.492046356201172
+- -4.534677505493164
+- -4.477104187011719
+- -4.511618614196777
+- -4.387601375579834
+- -4.499236106872559
+- -4.3717169761657715
+- -4.4242024421691895
+- -4.4055657386779785
+- -4.429355144500732
+- -4.4636993408203125
+- -4.508528232574463
+- -4.515079498291016
+- -4.426190376281738
+- -4.433525085449219
+- -4.4200215339660645
+- -4.421280860900879
+- -4.400143623352051
+- -4.419166088104248
+- -4.429825305938721
+- -4.436781406402588
+- -4.51550817489624
+- -4.518474578857422
+- -4.495880603790283
+- -4.483924865722656
+- -4.409562587738037
+- -4.3811845779418945
+- -4.411908149719238
+- -4.427165985107422
+- -4.396549701690674
+- -4.340637683868408
+- -4.405435085296631
+- -4.367630481719971
+- -4.419083595275879
+- -4.389026165008545
+- -4.371067047119141
+- -4.370710372924805
+- -4.3755269050598145
+- -4.39500093460083
+- -4.451773166656494
+- -4.365351676940918
+- -4.348028182983398
+- -4.408270359039307
+- -4.390385627746582
+- -4.347931861877441
+- -4.378237247467041
+- -4.426717758178711
+- -4.364233493804932
+- -4.371546745300293
+- -4.402477264404297
+- -4.430750846862793
+- -4.404538154602051
+- -4.384459018707275
+- -4.401677131652832
+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/HokoHifi

checkpoints/Unnamed/lightning_logs/lastest/hparams.yaml ADDED Viewed

	@@ -0,0 +1 @@


1	+ {}

checkpoints/Unnamed/model_ckpt_steps_192000.ckpt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c441462923580893a6170dd00126084be0a20b387b1c4fb1860755acd36c881b
+size 391390823

checkpoints/nsf_hifigan/NOTICE.txt ADDED Viewed

	@@ -0,0 +1,74 @@

+--- DiffSinger Community Vocoder ---
+ARCHITECTURE: NSF-HiFiGAN
+RELEASE DATE: 2022-12-11
+HYPER PARAMETERS:
+ - 44100 sample rate
+ - 128 mel bins
+ - 512 hop size
+ - 2048 window size
+ - fmin at 40Hz
+ - fmax at 16000Hz
+NOTICE:
+All model weights in the [DiffSinger Community Vocoder Project](https://openvpi.github.io/vocoders/), including
+model weights in this directory, are provided by the [OpenVPI Team](https://github.com/openvpi/), under the
+[Attribution-NonCommercial-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
+ACKNOWLEDGEMENTS:
+Training data of this vocoder is provided and permitted by the following organizations, societies and individuals:
+孙飒              https://www.qfssr.cn
+赤松_Akamatsu     https://www.zhibin.club
+乐威              https://www.zhibin.club
+伯添              https://space.bilibili.com/24087011
+雲宇光             https://space.bilibili.com/660675050
+橙子言             https://space.bilibili.com/318486464
+人衣大人           https://space.bilibili.com/2270344
+玖蝶              https://space.bilibili.com/676771003
+Yuuko
+白夜零BYL          https://space.bilibili.com/1605040503
+嗷天              https://space.bilibili.com/5675252
+洛泠羽            https://space.bilibili.com/347373318
+灰条纹的灰猫君      https://space.bilibili.com/2083633
+幽寂              https://space.bilibili.com/478860
+恶魔王女           https://space.bilibili.com/2475098
+AlexYHX 芮晴
+绮萱              https://y.qq.com/n/ryqq/singer/003HjD6H4aZn1K
+诗芸              https://y.qq.com/n/ryqq/singer/0005NInj142zm0
+汐蕾              https://y.qq.com/n/ryqq/singer/0023cWMH1Bq1PJ
+1262917464
+炜阳
+叶卡yolka
+幸の夏            https://space.bilibili.com/1017297686
+暮色未量           https://space.bilibili.com/272904686
+晓寞sama          https://space.bilibili.com/3463394
+没头绪的节操君
+串串BunC          https://space.bilibili.com/95817834
+落雨              https://space.bilibili.com/1292427
+长尾巴的翎艾        https://space.bilibili.com/1638666
+声闻计划           https://space.bilibili.com/392812269
+唐家大小姐         http://5sing.kugou.com/palmusic/default.html
+不伊子
+Training machines are provided by:
+花儿不哭           https://space.bilibili.com/5760446
+TERMS OF REDISTRIBUTIONS:
+1. Do not sell this vocoder, or charge any fees from redistributing it, as prohibited by
+   the license.
+2. Include a copy of the CC BY-NC-SA 4.0 license, or a link referring to it.
+3. Include a copy of this notice, or any other notices informing that this vocoder is
+   provided by the OpenVPI Team, that this vocoder is licensed under CC BY-NC-SA 4.0, and
+   with a complete acknowledgement list as shown above.
+4. If you fine-tuned or modified the weights, leave a notice about what has been changed.
+5. (Optional) Leave a link to the official release page of the vocoder, and tell users
+   that other versions and future updates of this vocoder can be obtained from the website.

checkpoints/nsf_hifigan/NOTICE.zh-CN.txt ADDED Viewed

	@@ -0,0 +1,72 @@

+--- DiffSinger 社区声码器 ---
+架构：NSF-HiFiGAN
+发布日期：2022-12-11
+超参数：
+ - 44100 sample rate
+ - 128 mel bins
+ - 512 hop size
+ - 2048 window size
+ - fmin at 40Hz
+ - fmax at 16000Hz
+注意事项：
+[DiffSinger 社区声码器企划](https://openvpi.github.io/vocoders/) 中的所有模型权重，
+包括此目录下的模型权重，均由 [OpenVPI Team](https://github.com/openvpi/) 提供，并基于
+[Attribution-NonCommercial-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+进行许可。
+致谢：
+此声码器的训练数据由以下组织、社团和个人提供并许可：
+孙飒              https://www.qfssr.cn
+赤松_Akamatsu     https://www.zhibin.club
+乐威              https://www.zhibin.club
+伯添              https://space.bilibili.com/24087011
+雲宇光             https://space.bilibili.com/660675050
+橙子言             https://space.bilibili.com/318486464
+人衣大人           https://space.bilibili.com/2270344
+玖蝶              https://space.bilibili.com/676771003
+Yuuko
+白夜零BYL          https://space.bilibili.com/1605040503
+嗷天              https://space.bilibili.com/5675252
+洛泠羽            https://space.bilibili.com/347373318
+灰条纹的灰猫君      https://space.bilibili.com/2083633
+幽寂              https://space.bilibili.com/478860
+恶魔王女           https://space.bilibili.com/2475098
+AlexYHX 芮晴
+绮萱              https://y.qq.com/n/ryqq/singer/003HjD6H4aZn1K
+诗芸              https://y.qq.com/n/ryqq/singer/0005NInj142zm0
+汐蕾              https://y.qq.com/n/ryqq/singer/0023cWMH1Bq1PJ
+1262917464
+炜阳
+叶卡yolka
+幸の夏            https://space.bilibili.com/1017297686
+暮色未量           https://space.bilibili.com/272904686
+晓寞sama          https://space.bilibili.com/3463394
+没头绪的节操君
+串串BunC          https://space.bilibili.com/95817834
+落雨              https://space.bilibili.com/1292427
+长尾巴的翎艾        https://space.bilibili.com/1638666
+声闻计划           https://space.bilibili.com/392812269
+唐家大小姐         http://5sing.kugou.com/palmusic/default.html
+不伊子
+训练算力的提供者如下：
+花儿不哭           https://space.bilibili.com/5760446
+二次分发条款：
+1. 请勿售卖此声码器或从其二次分发过程中收取任何费用，因为此类行为受到许可证的禁止。
+2. 请在二次分发文件中包含一份 CC BY-NC-SA 4.0 许可证的副本或指向该许可证的链接。
+3. 请在二次分发文件中包含这份声明，或以其他形式声明此声码器由 OpenVPI Team 提供并基于 CC BY-NC-SA 4.0 许可，
+   并附带上述完整的致谢名单。
+4. 如果您微调或修改了权重，请留下一份关于其受到了何种修改的说明。
+5.（可选）留下一份指向此声码器的官方发布页面的链接，并告知使用者可从该网站获取此声码器的其他版本和未来的更新。

checkpoints/nsf_hifigan/config.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+    "resblock": "1",
+    "num_gpus": 4,
+    "batch_size": 10,
+    "learning_rate": 0.0002,
+    "adam_b1": 0.8,
+    "adam_b2": 0.99,
+    "lr_decay": 0.999,
+    "seed": 1234,
+    "upsample_rates":        [ 8, 8, 2, 2, 2],
+    "upsample_kernel_sizes": [16,16, 4, 4, 4],
+    "upsample_initial_channel": 512,
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "discriminator_periods": [3, 5, 7, 11, 17, 23, 37],
+    "segment_size": 16384,
+    "num_mels": 128,
+    "num_freq": 1025,
+    "n_fft"   : 2048,
+    "hop_size": 512,
+    "win_size": 2048,
+    "sampling_rate": 44100,
+    "fmin": 40,
+    "fmax": 16000,
+    "fmax_for_loss": null,
+    "num_workers": 16,
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54321",
+        "world_size": 1
+    }
+}

checkpoints/nsf_hifigan/model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c576b63b7ed952161b70fad34e0562ace502ce689195520d8a2a6c051de29d6
+size 56825430