Text-to-Speech
Fairseq
Chinese
audio
Changhan's picture
Upload hifigan.json
15a6dbf
raw
history blame
762 Bytes
{
"resblock": "1",
"num_gpus": 0,
"batch_size": 16,
"learning_rate": 0.0002,
"adam_b1": 0.8,
"adam_b2": 0.99,
"lr_decay": 0.999,
"seed": 1234,
"upsample_rates": [8,8,2,2],
"upsample_kernel_sizes": [16,16,4,4],
"upsample_initial_channel": 512,
"resblock_kernel_sizes": [3,7,11],
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
"segment_size": 8192,
"num_mels": 80,
"num_freq": 1025,
"n_fft": 1024,
"hop_size": 256,
"win_size": 1024,
"sampling_rate": 22050,
"fmin": 0,
"fmax": 8000,
"fmax_for_loss": null,
"num_workers": 4,
"dist_config": {
"dist_backend": "nccl",
"dist_url": "tcp://localhost:54321",
"world_size": 1
}
}