Hugging Face's logo

farnad
/
synth_SW_LF_AC

Diffusers
TensorBoard
Safetensors
AudioDiffusionPipeline
Model card Files
xet
Metrics Community
farnad commited on
Commit
8effc68
·
verified ·
1 Parent(s): 596666f

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. logs/train_unet/events.out.tfevents.1730372115.ip-10-0-231-206.eu-west-1.compute.internal.30.0 +3 -0
  2. mel/mel_config.json +11 -0
  3. model.tar.gz +3 -0
  4. model_index.json +20 -0
  5. scheduler/scheduler_config.json +19 -0
  6. unet/config.json +52 -0
  7. unet/diffusion_pytorch_model.safetensors +3 -0
logs/train_unet/events.out.tfevents.1730372115.ip-10-0-231-206.eu-west-1.compute.internal.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c1c625211bbdfa020d5f85f4356b31546005b4d31c3d4b587630c438b9f9d0
3
+ size 35911728
mel/mel_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Mel",
3
+ "_diffusers_version": "0.27.2",
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.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d6ff47e19930405c796d969975a8a878078364146f715ab268b285ca0e1738
3
+ size 452952711
model_index.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AudioDiffusionPipeline",
3
+ "_diffusers_version": "0.27.2",
4
+ "mel": [
5
+ "audiodiffusion.mel",
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.27.2",
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
+ "steps_offset": 0,
15
+ "thresholding": false,
16
+ "timestep_spacing": "leading",
17
+ "trained_betas": null,
18
+ "variance_type": "fixed_small"
19
+ }
unet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DModel",
3
+ "_diffusers_version": "0.27.2",
4
+ "_name_or_path": "/root/.cache/huggingface/hub/models--teticio--audio-diffusion-256/snapshots/a098cdacf70bcbc28c6f2927824e18792f756f8f/unet",
5
+ "act_fn": "silu",
6
+ "add_attention": true,
7
+ "attention_head_dim": 8,
8
+ "attn_norm_num_groups": null,
9
+ "block_out_channels": [
10
+ 128,
11
+ 128,
12
+ 256,
13
+ 256,
14
+ 512,
15
+ 512
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "down_block_types": [
20
+ "DownBlock2D",
21
+ "DownBlock2D",
22
+ "DownBlock2D",
23
+ "DownBlock2D",
24
+ "AttnDownBlock2D",
25
+ "DownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "downsample_type": "conv",
29
+ "dropout": 0.0,
30
+ "flip_sin_to_cos": true,
31
+ "freq_shift": 0,
32
+ "in_channels": 1,
33
+ "layers_per_block": 2,
34
+ "mid_block_scale_factor": 1,
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "num_train_timesteps": null,
39
+ "out_channels": 1,
40
+ "resnet_time_scale_shift": "default",
41
+ "sample_size": 256,
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 sha256:60e640d4d3171a891db91401293e7c05493b11c3febe2f43585f8e0b9cea819a
3
+ size 454722660