TimoH commited on
Commit
4bab98d
1 Parent(s): daceb8e

Upload model, initial commit

Browse files
mel/mel_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Mel",
3
+ "_diffusers_version": "0.24.0",
4
+ "hop_length": 256,
5
+ "n_fft": 1024,
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": "0.24.0",
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
+ null,
18
+ null
19
+ ]
20
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.24.0",
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
+ "sample_max_value": 1.0,
13
+ "steps_offset": 0,
14
+ "thresholding": false,
15
+ "timestep_spacing": "leading",
16
+ "trained_betas": null,
17
+ "variance_type": "fixed_small"
18
+ }
unet/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.24.0",
4
+ "act_fn": "silu",
5
+ "add_attention": true,
6
+ "attention_head_dim": 8,
7
+ "attn_norm_num_groups": null,
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
+ "dropout": 0.0,
29
+ "flip_sin_to_cos": true,
30
+ "freq_shift": 0,
31
+ "in_channels": 1,
32
+ "layers_per_block": 2,
33
+ "mid_block_scale_factor": 1,
34
+ "norm_eps": 1e-05,
35
+ "norm_num_groups": 32,
36
+ "num_class_embeds": null,
37
+ "num_train_timesteps": null,
38
+ "out_channels": 1,
39
+ "resnet_time_scale_shift": "default",
40
+ "sample_size": [
41
+ 256,
42
+ 256
43
+ ],
44
+ "time_embedding_type": "positional",
45
+ "up_block_types": [
46
+ "UpBlock2D",
47
+ "AttnUpBlock2D",
48
+ "UpBlock2D",
49
+ "UpBlock2D",
50
+ "UpBlock2D",
51
+ "UpBlock2D"
52
+ ],
53
+ "upsample_type": "conv"
54
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41994fed07c3991aa4522a507b6b3585f69ecfc085c0b60f3b7a2ebc9131ebd3
3
+ size 454722660