AudioGPT / NeuralSeq /egs /egs_bases /svs /popcs_ds_beta6.yaml
Datasculptor's picture
Duplicate from AIGC-Audio/AudioGPT
98f685a
base_config:
- configs/tts/fs2.yaml
- configs/singing/base.yaml
- ./base.yaml
audio_sample_rate: 24000
hop_size: 128 # Hop size.
fft_size: 512 # FFT size.
win_size: 512 # FFT size.
fmin: 30
fmax: 12000
min_level_db: -120
binarization_args:
with_wav: true
with_spk_embed: false
with_align: true
raw_data_dir: 'data/raw/popcs'
processed_data_dir: 'data/processed/popcs'
binary_data_dir: 'data/binary/popcs-pmf0'
num_spk: 1
datasets: [
'popcs',
]
test_prefixes: [
'popcs-说散就散',
'popcs-隐形的翅膀',
]
spec_min: [-6.8276, -7.0270, -6.8142, -7.1429, -7.6669, -7.6000, -7.1148, -6.9640,
-6.8414, -6.6596, -6.6880, -6.7439, -6.7986, -7.4940, -7.7845, -7.6586,
-6.9288, -6.7639, -6.9118, -6.8246, -6.7183, -7.1769, -6.9794, -7.4513,
-7.3422, -7.5623, -6.9610, -6.8158, -6.9595, -6.8403, -6.5688, -6.6356,
-7.0209, -6.5002, -6.7819, -6.5232, -6.6927, -6.5701, -6.5531, -6.7069,
-6.6462, -6.4523, -6.5954, -6.4264, -6.4487, -6.7070, -6.4025, -6.3042,
-6.4008, -6.3857, -6.3903, -6.3094, -6.2491, -6.3518, -6.3566, -6.4168,
-6.2481, -6.3624, -6.2858, -6.2575, -6.3638, -6.4520, -6.1835, -6.2754,
-6.1253, -6.1645, -6.0638, -6.1262, -6.0710, -6.1039, -6.4428, -6.1363,
-6.1054, -6.1252, -6.1797, -6.0235, -6.0758, -5.9453, -6.0213, -6.0446]
spec_max: [ 0.2645, 0.0583, -0.2344, -0.0184, 0.1227, 0.1533, 0.1103, 0.1212,
0.2421, 0.1809, 0.2134, 0.3161, 0.3301, 0.3289, 0.2667, 0.2421,
0.2581, 0.2600, 0.1394, 0.1907, 0.1082, 0.1474, 0.1680, 0.2550,
0.1057, 0.0826, 0.0423, 0.1203, -0.0701, -0.0056, 0.0477, -0.0639,
-0.0272, -0.0728, -0.1648, -0.0855, -0.2652, -0.1998, -0.1547, -0.2167,
-0.4181, -0.5463, -0.4161, -0.4733, -0.6518, -0.5387, -0.4290, -0.4191,
-0.4151, -0.3042, -0.3810, -0.4160, -0.4496, -0.2847, -0.4676, -0.4658,
-0.4931, -0.4885, -0.5547, -0.5481, -0.6948, -0.7968, -0.8455, -0.8392,
-0.8770, -0.9520, -0.8749, -0.7297, -0.8374, -0.8667, -0.7157, -0.9035,
-0.9219, -0.8801, -0.9298, -0.9009, -0.9604, -1.0537, -1.0781, -1.3766]
task_cls: tasks.svs.diffsinger_task.DiffSingerTask
#vocoder: tasks.svs.singingvocoder.highgan.HighGAN
#vocoder_ckpt: checkpoints/h_2_model/checkpoint-530000steps.pkl
vocoder: vocoders.hifigan.HifiGAN
vocoder_ckpt: checkpoints/0109_hifigan_bigpopcs_hop128
pitch_extractor: 'parselmouth'
# config for experiments
use_spk_embed: false
num_valid_plots: 10
max_updates: 160000
lr: 0.001
timesteps: 100
K_step: 51
diff_loss_type: l1
diff_decoder_type: 'wavenet'
schedule_type: 'linear'
max_beta: 0.06
fs2_ckpt: ''
use_nsf: true