Hugging Face's logo

teticio
/
latent-audio-diffusion-ddim-256

Diffusers
TensorBoard
AudioDiffusionPipeline
audio
spectrograms
Model card Files Metrics Community
teticio commited on
Commit
0e52a64
•
1 Parent(s): c7d19fe

Epoch 9

Browse files
Files changed (8) hide show
  1. .gitignore +1 -0
  2. logs/train_unconditional/events.out.tfevents.1667657492.cucumber.2271985.0 +3 -0
  3. model_index.json +16 -0
  4. scheduler/scheduler_config.json +12 -0
  5. unet/config.json +45 -0
  6. unet/diffusion_pytorch_model.bin +3 -0
  7. vqvae/config.json +30 -0
  8. vqvae/diffusion_pytorch_model.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
logs/train_unconditional/events.out.tfevents.1667657492.cucumber.2271985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5607be65eedb1b8e09b8ecd5f24ab2f08ec169d228451ad1dc9e625d54ca18cc
3
+ size 2360282
model_index.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LatentAudioDiffusionPipeline",
3
+ "_diffusers_version": "0.8.0.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "DDIMScheduler"
7
+ ],
8
+ "unet": [
9
+ "diffusers",
10
+ "UNet2DModel"
11
+ ],
12
+ "vqvae": [
13
+ "diffusers",
14
+ "AutoencoderKL"
15
+ ]
16
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.8.0.dev0",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.0001,
7
+ "clip_sample": true,
8
+ "num_train_timesteps": 1000,
9
+ "set_alpha_to_one": true,
10
+ "steps_offset": 0,
11
+ "trained_betas": null
12
+ }
unet/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.8.0.dev0",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 8,
6
+ "block_out_channels": [
7
+ 128,
8
+ 128,
9
+ 256,
10
+ 256,
11
+ 512,
12
+ 512
13
+ ],
14
+ "center_input_sample": false,
15
+ "down_block_types": [
16
+ "DownBlock2D",
17
+ "DownBlock2D",
18
+ "DownBlock2D",
19
+ "DownBlock2D",
20
+ "AttnDownBlock2D",
21
+ "DownBlock2D"
22
+ ],
23
+ "downsample_padding": 1,
24
+ "flip_sin_to_cos": true,
25
+ "freq_shift": 0,
26
+ "in_channels": 1,
27
+ "layers_per_block": 2,
28
+ "mid_block_scale_factor": 1,
29
+ "norm_eps": 1e-05,
30
+ "norm_num_groups": 32,
31
+ "out_channels": 1,
32
+ "sample_size": [
33
+ 32,
34
+ 32
35
+ ],
36
+ "time_embedding_type": "positional",
37
+ "up_block_types": [
38
+ "UpBlock2D",
39
+ "AttnUpBlock2D",
40
+ "UpBlock2D",
41
+ "UpBlock2D",
42
+ "UpBlock2D",
43
+ "UpBlock2D"
44
+ ]
45
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c019cca4f89cfe0ce59ef1704f2ae58b8455f3532a616321461f3e9ee09f4e6b
3
+ size 454840957
vqvae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.8.0.dev0",
4
+ "_name_or_path": "models/autoencoder-kl",
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
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vqvae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3947218cbdf1000b8eff97dea4418e0388d484cbc201726b17883e996cd47c
3
+ size 334526033