|
| 1 | +import os |
| 2 | +import argparse |
| 3 | +from tqdm import tqdm |
| 4 | +from random import shuffle |
| 5 | +import json |
| 6 | +config_template = { |
| 7 | + "train": { |
| 8 | + "log_interval": 200, |
| 9 | + "eval_interval": 200, |
| 10 | + "seed": 1234, |
| 11 | + "epochs": 10000, |
| 12 | + "learning_rate": 2e-4, |
| 13 | + "betas": [0.8, 0.99], |
| 14 | + "eps": 1e-9, |
| 15 | + "batch_size": 16, |
| 16 | + "fp16_run": False, |
| 17 | + "lr_decay": 0.999875, |
| 18 | + "segment_size": 17920, |
| 19 | + "init_lr_ratio": 1, |
| 20 | + "warmup_epochs": 0, |
| 21 | + "c_mel": 45, |
| 22 | + "c_kl": 1.0, |
| 23 | + "use_sr": True, |
| 24 | + "max_speclen": 384, |
| 25 | + "port": "8001" |
| 26 | + }, |
| 27 | + "data": { |
| 28 | + "training_files":"filelists/train.txt", |
| 29 | + "validation_files":"filelists/val.txt", |
| 30 | + "max_wav_value": 32768.0, |
| 31 | + "sampling_rate": 48000, |
| 32 | + "filter_length": 1280, |
| 33 | + "hop_length": 320, |
| 34 | + "win_length": 1280, |
| 35 | + "n_mel_channels": 80, |
| 36 | + "mel_fmin": 0.0, |
| 37 | + "mel_fmax": None |
| 38 | + }, |
| 39 | + "model": { |
| 40 | + "inter_channels": 192, |
| 41 | + "hidden_channels": 192, |
| 42 | + "filter_channels": 768, |
| 43 | + "n_heads": 2, |
| 44 | + "n_layers": 6, |
| 45 | + "kernel_size": 3, |
| 46 | + "p_dropout": 0.1, |
| 47 | + "resblock": "1", |
| 48 | + "resblock_kernel_sizes": [3,7,11], |
| 49 | + "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]], |
| 50 | + "upsample_rates": [10,8,2,2], |
| 51 | + "upsample_initial_channel": 512, |
| 52 | + "upsample_kernel_sizes": [16,16,4,4], |
| 53 | + "n_layers_q": 3, |
| 54 | + "use_spectral_norm": False, |
| 55 | + "gin_channels": 256, |
| 56 | + "ssl_dim": 256, |
| 57 | + "n_speakers": 0, |
| 58 | + }, |
| 59 | + "spk":{ |
| 60 | + "nen": 0, |
| 61 | + "paimon": 1, |
| 62 | + "yunhao": 2 |
| 63 | + } |
| 64 | +} |
| 65 | + |
| 66 | + |
| 67 | +if __name__ == "__main__": |
| 68 | + parser = argparse.ArgumentParser() |
| 69 | + parser.add_argument("--train_list", type=str, default="./filelists/train.txt", help="path to train list") |
| 70 | + parser.add_argument("--val_list", type=str, default="./filelists/val.txt", help="path to val list") |
| 71 | + parser.add_argument("--test_list", type=str, default="./filelists/test.txt", help="path to test list") |
| 72 | + parser.add_argument("--source_dir", type=str, default="./dataset/48k", help="path to source dir") |
| 73 | + args = parser.parse_args() |
| 74 | + |
| 75 | + train = [] |
| 76 | + val = [] |
| 77 | + test = [] |
| 78 | + idx = 0 |
| 79 | + spk_dict = {} |
| 80 | + spk_id = 0 |
| 81 | + for speaker in tqdm(os.listdir(args.source_dir)): |
| 82 | + spk_dict[speaker] = spk_id |
| 83 | + spk_id += 1 |
| 84 | + wavs = [os.path.join(args.source_dir, speaker, i)for i in os.listdir(os.path.join(args.source_dir, speaker))] |
| 85 | + wavs = [i for i in wavs if i.endswith("wav")] |
| 86 | + shuffle(wavs) |
| 87 | + train += wavs[2:-10] |
| 88 | + val += wavs[:2] |
| 89 | + test += wavs[-10:] |
| 90 | + n_speakers = len(spk_dict.keys())*2 |
| 91 | + shuffle(train) |
| 92 | + shuffle(val) |
| 93 | + shuffle(test) |
| 94 | + |
| 95 | + print("Writing", args.train_list) |
| 96 | + with open(args.train_list, "w") as f: |
| 97 | + for fname in tqdm(train): |
| 98 | + wavpath = fname |
| 99 | + f.write(wavpath + "\n") |
| 100 | + |
| 101 | + print("Writing", args.val_list) |
| 102 | + with open(args.val_list, "w") as f: |
| 103 | + for fname in tqdm(val): |
| 104 | + wavpath = fname |
| 105 | + f.write(wavpath + "\n") |
| 106 | + |
| 107 | + print("Writing", args.test_list) |
| 108 | + with open(args.test_list, "w") as f: |
| 109 | + for fname in tqdm(test): |
| 110 | + wavpath = fname |
| 111 | + f.write(wavpath + "\n") |
| 112 | + |
| 113 | + config_template["model"]["n_speakers"] = n_speakers |
| 114 | + config_template["spk"] = spk_dict |
| 115 | + print("Writing configs/config.json") |
| 116 | + with open("configs/config.json", "w") as f: |
| 117 | + json.dump(config_template, f, indent=2) |
0 commit comments