tvergho commited on
Commit
406b041
1 Parent(s): a133101
logs/train_unet/events.out.tfevents.1677551874.db73ffa72954.3211.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49741d36a67bb0443fb843a833fb9481244dcfc7deebf206a6fbd96ed9edd83
3
+ size 75832
mel/mel_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Mel",
3
+ "_diffusers_version": "0.13.1",
4
+ "hop_length": 1024,
5
+ "n_fft": 2048,
6
+ "n_iter": 32,
7
+ "sample_rate": 22050,
8
+ "top_db": 80,
9
+ "x_res": 512,
10
+ "y_res": 512
11
+ }
model_index.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioDiffusionPipeline",
3
+ "_diffusers_version": "0.13.1",
4
+ "mel": [
5
+ "audio_diffusion",
6
+ "Mel"
7
+ ],
8
+ "scheduler": [
9
+ "diffusers",
10
+ "DDPMScheduler"
11
+ ],
12
+ "unet": [
13
+ "diffusers",
14
+ "UNet2DModel"
15
+ ],
16
+ "vqvae": [
17
+ "diffusers",
18
+ "AutoencoderKL"
19
+ ]
20
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.13.1",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.0001,
7
+ "clip_sample": true,
8
+ "clip_sample_range": 1.0,
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "epsilon",
11
+ "trained_betas": null,
12
+ "variance_type": "fixed_small"
13
+ }
unet/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.13.1",
4
+ "act_fn": "silu",
5
+ "add_attention": true,
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 128,
9
+ 128,
10
+ 256,
11
+ 256,
12
+ 512,
13
+ 512
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "down_block_types": [
18
+ "DownBlock2D",
19
+ "DownBlock2D",
20
+ "DownBlock2D",
21
+ "DownBlock2D",
22
+ "AttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "downsample_padding": 1,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 1,
29
+ "layers_per_block": 2,
30
+ "mid_block_scale_factor": 1,
31
+ "norm_eps": 1e-05,
32
+ "norm_num_groups": 32,
33
+ "num_class_embeds": null,
34
+ "out_channels": 1,
35
+ "resnet_time_scale_shift": "default",
36
+ "sample_size": [
37
+ 64,
38
+ 64
39
+ ],
40
+ "time_embedding_type": "positional",
41
+ "up_block_types": [
42
+ "UpBlock2D",
43
+ "AttnUpBlock2D",
44
+ "UpBlock2D",
45
+ "UpBlock2D",
46
+ "UpBlock2D",
47
+ "UpBlock2D"
48
+ ]
49
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b1bc7682c23c56af9da90ba630c1ec733097e8757df4dc2bf9f790beeef7c6
3
+ size 454848893
vqvae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.1",
4
+ "_name_or_path": "/root/.cache/huggingface/diffusers/models--teticio--latent-audio-diffusion-512/snapshots/51f63aeea6e6e68aeb2600e3cd1ab36dfd8da541/vqvae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 1,
19
+ "latent_channels": 1,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 1,
23
+ "sample_size": 256,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vqvae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ea3b3045c2f813827234e91dda6a16adef52ef91ec2f387f07c8034da2daac
3
+ size 334530673