RMSnow's picture
add backend inference and inferface output
0883aa1
{
"base_config": "config/base.json",
"model_type": "AudioLDM",
"task_type": "tta",
"dataset": [
"AudioCaps"
],
"preprocess": {
// feature used for model training
"use_spkid": false,
"use_uv": false,
"use_frame_pitch": false,
"use_phone_pitch": false,
"use_frame_energy": false,
"use_phone_energy": false,
"use_mel": false,
"use_audio": false,
"use_label": false,
"use_one_hot": false,
"cond_mask_prob": 0.1
},
// model
"model": {
"audioldm": {
"image_size": 32,
"in_channels": 4,
"out_channels": 4,
"model_channels": 256,
"attention_resolutions": [
4,
2,
1
],
"num_res_blocks": 2,
"channel_mult": [
1,
2,
4
],
"num_heads": 8,
"use_spatial_transformer": true,
"transformer_depth": 1,
"context_dim": 768,
"use_checkpoint": true,
"legacy": false
},
"autoencoderkl": {
"ch": 128,
"ch_mult": [
1,
1,
2,
2,
4
],
"num_res_blocks": 2,
"in_channels": 1,
"z_channels": 4,
"out_ch": 1,
"double_z": true
},
"noise_scheduler": {
"num_train_timesteps": 1000,
"beta_start": 0.00085,
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"clip_sample": false,
"steps_offset": 1,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"prediction_type": "epsilon"
}
},
// train
"train": {
"lronPlateau": {
"factor": 0.9,
"patience": 100,
"min_lr": 4.0e-5,
"verbose": true
},
"adam": {
"lr": 5.0e-5,
"betas": [
0.9,
0.999
],
"weight_decay": 1.0e-2,
"eps": 1.0e-8
}
}
}