Hugging Face's logo

sebascorreia
/
edm_set_model

Diffusers
TensorBoard
Safetensors
AudioDiffusionPipeline
Model card Files Metrics Community
sebascorreia commited on
Commit
025b533
·
1 Parent(s): 2d39ce9

Epoch 0

Browse files
Files changed (6) hide show
  1. logs/train_unet/events.out.tfevents.1693227946.c2d003a6aba9.3928.0 +3 -0
  2. mel/mel_config.json +11 -0
  3. model_index.json +20 -0
  4. scheduler/scheduler_config.json +19 -0
  5. unet/config.json +52 -0
  6. unet/diffusion_pytorch_model.safetensors +3 -0
logs/train_unet/events.out.tfevents.1693227946.c2d003a6aba9.3928.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a57c6b10bf0ef0466e57b717a4f1e323c44904681535a91411bf04590ccbfa
3
+ size 64855
mel/mel_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Mel",
3
+ "_diffusers_version": "0.20.1",
4
+ "hop_length": 512,
5
+ "n_fft": 2048,
6
+ "n_iter": 32,
7
+ "sample_rate": 22050,
8
+ "top_db": 80,
9
+ "x_res": 256,
10
+ "y_res": 256
11
+ }
model_index.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioDiffusionPipeline",
3
+ "_diffusers_version": "0.20.1",
4
+ "mel": [
5
+ "audio_diffusion",
6
+ "Mel"
7
+ ],
8
+ "scheduler": [
9
+ "diffusers",
10
+ "DDIMScheduler"
11
+ ],
12
+ "unet": [
13
+ "diffusers",
14
+ "UNet2DModel"
15
+ ],
16
+ "vqvae": [
17
+ null,
18
+ null
19
+ ]
20
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.20.1",
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
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": true,
15
+ "steps_offset": 0,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
+ "trained_betas": null
19
+ }
unet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.20.1",
4
+ "_name_or_path": "/root/.cache/huggingface/hub/models--sebascorreia--imagenet_encoding_audiodiffusion/snapshots/076c3f502b0a18694e30e72d9b5714b4980d62a5/unet",
5
+ "act_fn": "silu",
6
+ "add_attention": true,
7
+ "attention_head_dim": 8,
8
+ "block_out_channels": [
9
+ 128,
10
+ 128,
11
+ 256,
12
+ 256,
13
+ 512,
14
+ 512
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "down_block_types": [
19
+ "DownBlock2D",
20
+ "DownBlock2D",
21
+ "DownBlock2D",
22
+ "DownBlock2D",
23
+ "AttnDownBlock2D",
24
+ "DownBlock2D"
25
+ ],
26
+ "downsample_padding": 1,
27
+ "downsample_type": "conv",
28
+ "flip_sin_to_cos": true,
29
+ "freq_shift": 0,
30
+ "in_channels": 1,
31
+ "layers_per_block": 2,
32
+ "mid_block_scale_factor": 1,
33
+ "norm_eps": 1e-05,
34
+ "norm_num_groups": 32,
35
+ "num_class_embeds": null,
36
+ "out_channels": 1,
37
+ "resnet_time_scale_shift": "default",
38
+ "sample_size": [
39
+ 256,
40
+ 256
41
+ ],
42
+ "time_embedding_type": "positional",
43
+ "up_block_types": [
44
+ "UpBlock2D",
45
+ "AttnUpBlock2D",
46
+ "UpBlock2D",
47
+ "UpBlock2D",
48
+ "UpBlock2D",
49
+ "UpBlock2D"
50
+ ],
51
+ "upsample_type": "conv"
52
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c490ab7d0c0ca83e2ef6eb051b26000680bdaa1a355f49ab9932e8f9dc61979
3
+ size 454722660