Hugging Face's logo

teticio
/
latent-audio-diffusion-512

Diffusers
TensorBoard
AudioDiffusionPipeline
Model card Files
xet
Metrics Community
teticio commited on
Commit
ecbcfd4
·
1 Parent(s): f94b042

Epoch 9

Browse files
Files changed (8) hide show
  1. logs/train_unconditional/events.out.tfevents.1670840964.cucumber.51797.0 +3 -0
  2. mel/mel_config.json +11 -0
  3. model_index.json +20 -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
logs/train_unconditional/events.out.tfevents.1670840964.cucumber.51797.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d19aeea6eccde95a4cfbbaf983daa8ce12d4e9231d4e8d96b8a0bea6200857b
3
+ size 34900604
mel/mel_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Mel",
3
+ "_diffusers_version": "0.10.2",
4
+ "hop_length": 512,
5
+ "n_fft": 2000,
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": "0.10.2",
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.10.2",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.0001,
7
+ "clip_sample": true,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "trained_betas": null,
11
+ "variance_type": "fixed_small"
12
+ }
unet/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.10.2",
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
+ 64,
34
+ 64
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:b4f3db511fc354235051f5b1a2c35e22897313de9cc74cb8b4387d6700bd258f
3
+ size 454840957
vqvae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.10.2",
4
+ "_name_or_path": "../tmp/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 sha256:2faa4a7f2fefa2605115ff157a817f58c5ee578855e417ba42ec4bd473089bfb
3
+ size 334526033