Hugging Face's logo

heboya8
/
AudioLDM-log-13

Model card Files
xet
Community
heboya8 commited on
Commit
9fc6809
·
verified ·
1 Parent(s): a947f43

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. .gitattributes +0 -0
  2. latent_diffusion/my_configs/audioldm_original/audioldm_original.yaml +149 -0
  3. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/-Dtir74TiUM.wav +3 -0
  4. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/-SWaCArvQug.wav +3 -0
  5. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/04NjXsLyCl4.wav +3 -0
  6. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/05OJDYeHLMc.wav +3 -0
  7. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0ISHZQJdeSw.wav +3 -0
  8. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0Wdh45yt7tY.wav +3 -0
  9. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0nk7utNkHOY.wav +3 -0
  10. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/26jTWRMRoxY.wav +3 -0
  11. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/2RMOegT2Jn8.wav +3 -0
  12. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/2gvyOxKuQPY.wav +3 -0
  13. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/3IYd8cCmUkQ.wav +3 -0
  14. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/3Xoz87_SUdw.wav +3 -0
  15. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4M0njWKFsME.wav +3 -0
  16. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4i1aizhCnfg.wav +3 -0
  17. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4mtfOkzOvBI.wav +3 -0
  18. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/6iyinlZEgS4.wav +3 -0
  19. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/6uIOGE36tWo.wav +3 -0
  20. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/78S8DnvLQDY.wav +3 -0
  21. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/7_Sr2zv1sQc.wav +3 -0
  22. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/8Bu8CkR1xZY.wav +3 -0
  23. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/8sSV_vqOlS4.wav +3 -0
  24. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/A3vsvL-Yx0Q.wav +3 -0
  25. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/AHrUfa2H_5s.wav +3 -0
  26. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/B90BOtSOD2Q.wav +3 -0
  27. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Bl-lCgr5hGY.wav +3 -0
  28. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/ByOqw8M2U-Q.wav +3 -0
  29. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/CZoPTJNmiCw.wav +3 -0
  30. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Cy3HWnwMLyI.wav +3 -0
  31. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/D3f5VIJYR7M.wav +3 -0
  32. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/DW3z-ByrfWY.wav +3 -0
  33. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/EOaQnfDjVyo.wav +3 -0
  34. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Fa1c4qfBqzE.wav +3 -0
  35. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/HpkPTa1fQDE.wav +3 -0
  36. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Ie5FO_BetOE.wav +3 -0
  37. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/JRfU_hF1wdM.wav +3 -0
  38. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/JUrYWttZJBM.wav +3 -0
  39. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Jq2w30NYstQ.wav +3 -0
  40. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KOb-tRHYK68.wav +3 -0
  41. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KeSbjmMeyrY.wav +3 -0
  42. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KpwdlYIdtfs.wav +3 -0
  43. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/LAHWV6fZwUk.wav +3 -0
  44. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Ls6qMcgpdlM.wav +3 -0
  45. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/M5sptjrboqA.wav +3 -0
  46. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/NSyqj1DXZKg.wav +3 -0
  47. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/NzVg-cFQJbE.wav +3 -0
  48. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/OOik9i9wrU8.wav +3 -0
  49. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/TC4mH6nACm8.wav +3 -0
  50. latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/TkclVqlyKx4.wav +3 -0
.gitattributes CHANGED
The diff for this file is too large to render. See raw diff
 
latent_diffusion/my_configs/audioldm_original/audioldm_original.yaml ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ metadata_root: "./data/metadata/dataset_root.json"
2
+ log_directory: "./log/latent_diffusion"
3
+ project: "audioldm"
4
+ precision: "high"
5
+
6
+ variables:
7
+ sampling_rate: &sampling_rate 16000
8
+ mel_bins: &mel_bins 64
9
+ latent_embed_dim: &latent_embed_dim 8
10
+ latent_t_size: &latent_t_size 256 # TODO might need to change
11
+ latent_f_size: &latent_f_size 16
12
+ in_channels: &unet_in_channels 8
13
+ optimize_ddpm_parameter: &optimize_ddpm_parameter true
14
+ optimize_gpt: &optimize_gpt true
15
+ warmup_steps: &warmup_steps 2000
16
+
17
+ data:
18
+ train: ["audiocaps"]
19
+ val: "audiocaps"
20
+ test: "audiocaps"
21
+ class_label_indices: "audioset_eval_subset"
22
+ dataloader_add_ons: []
23
+
24
+ step:
25
+ validation_every_n_epochs: 5
26
+ save_checkpoint_every_n_steps: 40000
27
+ max_steps: 800000
28
+ save_top_k: 2
29
+
30
+ preprocessing:
31
+ audio:
32
+ sampling_rate: *sampling_rate
33
+ max_wav_value: 32768.0
34
+ duration: 10.24
35
+ stft:
36
+ filter_length: 1024
37
+ hop_length: 160
38
+ win_length: 1024
39
+ mel:
40
+ n_mel_channels: *mel_bins
41
+ mel_fmin: 0
42
+ mel_fmax: 8000
43
+ num_workers: 2
44
+
45
+ augmentation:
46
+ mixup: 0.0
47
+
48
+ addition_params:
49
+ gradient_accumulation_steps: 1
50
+
51
+ model:
52
+ target: audioldm_train.modules.latent_diffusion.ddpm.LatentDiffusion
53
+ params:
54
+ # Autoencoder
55
+ first_stage_config:
56
+ base_learning_rate: 8.0e-06
57
+ target: audioldm_train.modules.latent_encoder.autoencoder.AutoencoderKL
58
+ params:
59
+ reload_from_ckpt: "ckpts/vae_mel_16k_64bins.ckpt"
60
+ sampling_rate: *sampling_rate
61
+ batchsize: 3
62
+ monitor: val/rec_loss
63
+ image_key: fbank
64
+ subband: 1
65
+ embed_dim: *latent_embed_dim
66
+ time_shuffle: 1
67
+ lossconfig:
68
+ target: audioldm_train.losses.LPIPSWithDiscriminator
69
+ params:
70
+ disc_start: 50001
71
+ kl_weight: 1000.0
72
+ disc_weight: 0.5
73
+ disc_in_channels: 1
74
+ ddconfig:
75
+ double_z: true
76
+ mel_bins: *mel_bins # The frequency bins of mel spectrogram
77
+ z_channels: 8
78
+ resolution: 256
79
+ downsample_time: false
80
+ in_channels: 1
81
+ out_ch: 1
82
+ ch: 128
83
+ ch_mult:
84
+ - 1
85
+ - 2
86
+ - 4
87
+ num_res_blocks: 2
88
+ attn_resolutions: []
89
+ dropout: 0.0
90
+
91
+ # Other parameters
92
+ base_learning_rate: 1.0e-4
93
+ warmup_steps: *warmup_steps
94
+ optimize_ddpm_parameter: *optimize_ddpm_parameter
95
+ sampling_rate: *sampling_rate
96
+ batchsize: 1
97
+ linear_start: 0.0015
98
+ linear_end: 0.0195
99
+ num_timesteps_cond: 1
100
+ log_every_t: 200
101
+ timesteps: 1000
102
+ unconditional_prob_cfg: 0.1
103
+ parameterization: eps # [eps, x0, v]
104
+ first_stage_key: fbank
105
+ latent_t_size: *latent_t_size # TODO might need to change
106
+ latent_f_size: *latent_f_size
107
+ channels: *latent_embed_dim # TODO might need to change
108
+ monitor: val/loss_simple_ema
109
+ scale_by_std: true
110
+ unet_config:
111
+ target: audioldm_train.modules.diffusionmodules.openaimodel.UNetModel
112
+ params:
113
+ image_size: 64
114
+ extra_film_condition_dim: 512 # If you use film as extra condition, set this parameter. For example if you have two conditioning vectors each have dimension 512, then this number would be 1024
115
+ # context_dim:
116
+ # - 768
117
+ in_channels: *unet_in_channels # The input channel of the UNet model
118
+ out_channels: *latent_embed_dim # TODO might need to change
119
+ model_channels: 128 # TODO might need to change
120
+ attention_resolutions:
121
+ - 8
122
+ - 4
123
+ - 2
124
+ num_res_blocks: 2
125
+ channel_mult:
126
+ - 1
127
+ - 2
128
+ - 3
129
+ - 5
130
+ num_head_channels: 32
131
+ use_spatial_transformer: true
132
+ transformer_depth: 1
133
+ extra_sa_layer: false
134
+
135
+ cond_stage_config:
136
+ film_clap_cond1:
137
+ cond_stage_key: text
138
+ conditioning_key: film
139
+ target: audioldm_train.conditional_models.CLAPAudioEmbeddingClassifierFreev2
140
+ params:
141
+ pretrained_path: ckpts/clap_htsat_tiny.pt
142
+ sampling_rate: 16000
143
+ embed_mode: text # or text
144
+ amodel: HTSAT-tiny
145
+
146
+ evaluation_params:
147
+ unconditional_guidance_scale: 3.5
148
+ ddim_sampling_steps: 200
149
+ n_candidates_per_samples: 3
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/-Dtir74TiUM.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e538fe48a0c9b3d297063ed31a64f841558ad8d6e599daf5d01043dd0bf4bd5
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/-SWaCArvQug.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0c13eef07dd4e009e65d67cfe364ed7ccf400776229863c1c1bff5b20d4f7a
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/04NjXsLyCl4.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54bf60e6f04f3d1e0099eedc595329b09c63c5d0f6d57e82891f3a75587cb3e7
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/05OJDYeHLMc.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8de31ee9b4e354da63a785ab26be450d736b6693051354bc8114245544430e4
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0ISHZQJdeSw.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44c0195f912c239cfa3a24dfb860dc46028f926ec07897d4814d072bdc23c7e
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0Wdh45yt7tY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f551746f5bd5137a9afd2f47c93642b494742e625c8de826cc7a047ad322434
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/0nk7utNkHOY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff2c831d87bcd960bbd58fbd84035482df494bea26322f12910f5ff7b8f8c7a
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/26jTWRMRoxY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba163161d80a1391e54398e4764a5ce8654f2789761e097cdf8f197bf0d6d84
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/2RMOegT2Jn8.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0161a5031bed8833a6b5120b87744454d166bc1fc201e6e32ef6a78514c54b13
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/2gvyOxKuQPY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfd821d1988295cfcafbf4616a71257560a6d91e3b548a0fa581a1389fafb58
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/3IYd8cCmUkQ.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329d1a11478b8284e6475be8e5d4dfa3b647044c068be647fdd6d74d2f41a168
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/3Xoz87_SUdw.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c3232b0b161c6d2d3c0c545fe299c9fc2a0e25ee2dcbbefbd4afde98bbf183
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4M0njWKFsME.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8de7419c9622a0d84c27a2dc8e222a618f73685f64cf3124e018bc4dfb3201
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4i1aizhCnfg.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2743ed114750a5010e6e0b14f3ca00d35468e42c01dac6dfb7b2fdded92867
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/4mtfOkzOvBI.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05363df574522f2d26e273b4f7afd7ff5b3f67f2746f89e1a58d0d2990714a3d
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/6iyinlZEgS4.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a515e6b063b1a1c048d5632c714c860cd79146991882f960249e5d614035258b
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/6uIOGE36tWo.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28658c3fda4291e4331e71ef924efee0fe03891fd3d82916df5d08e769438907
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/78S8DnvLQDY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee972143e5c13de40a679f9a1fc96d86d58362be1c0f9d772d501b11f5d2c3e3
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/7_Sr2zv1sQc.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f1f926d3491885f1c84039773f7c8acd36cb382850775fa25b8f3510cafb51
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/8Bu8CkR1xZY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64c8ea6c92ce8493b5c13e514ff9a30d45fe3dffe362061cb9b8f7d5cadcaad
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/8sSV_vqOlS4.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d070cdec70950728f2e5e228724c3b0705de3b8dd736da7a71c88d1e77d507
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/A3vsvL-Yx0Q.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c129e9f209ced04b598fbd66ac1e0fd6c1df854079308849b2230f8a747b950
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/AHrUfa2H_5s.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbf1663a04ffb76393bc9fd38308671a5a2a934069ac37a2b7185539c8a3e80
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/B90BOtSOD2Q.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec4883376c5760f05b3c202812e74c85669184d087bb150e621422777e40d10
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Bl-lCgr5hGY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9ad8cdc723211cc5b159feace6ba87c8d0db0113762ef1d5bd48b473b4615e
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/ByOqw8M2U-Q.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4f2d74d3164d0ee407c488cd78d0006e4e527c1851f6de0d2f8f063e15588a
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/CZoPTJNmiCw.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a3dacc29ab1ef0e74c360f152826c6ef01036ca0fbd0a67fe2b47c60080400
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Cy3HWnwMLyI.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185cabfee33985a08bf22fbfc21e9d1b4f58d7b60a7753d6de93f8d2c52217aa
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/D3f5VIJYR7M.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c51ed135009c90105710c94cb7bbd9d13a324b5d21459241596c58aacb89f4c
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/DW3z-ByrfWY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfa8085d468278a3c5234d01e1148a5291ac5a5af06ad7def4aa32e3a4e9735
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/EOaQnfDjVyo.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd1f04f420b8444e940e60736afbac5a5e11d6eaff7acab023f5e3a087f3962
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Fa1c4qfBqzE.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b60c4ae8884d0fdc495e58cf5ec45f0b71b8b0e89a3b611d20325f64d98ff8
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/HpkPTa1fQDE.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4427f609f49798b264c28d74d13b626198c823c7e9fc20544266e8efb86149
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Ie5FO_BetOE.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c9524a1067eeea7c34dfe3a73463cf9b5859799d52103ef77bbf58f573c0da
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/JRfU_hF1wdM.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:308305eec05bb2d3c42fb27412b9bfed5ee28266ba2645c14cc3f82362ac199e
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/JUrYWttZJBM.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09badc66c097776dfe3b52a79c3f2813ac6d8da531c15739f6acb71bc50f43a0
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Jq2w30NYstQ.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efe204458cc486349b3dcdc5fc68b40fc2e342da361098426e7d15469795a83
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KOb-tRHYK68.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9956a0287a958cd95903caafb4207f744daae4a74538ab029f03c6bc7647fdb5
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KeSbjmMeyrY.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6d09a0a130aee9e867c38ae34d5866e7db2ccea3f6d6d7c87d95094c44890f
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/KpwdlYIdtfs.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6166cbe695bbaecfd8ba700cdf386a686b7cdfcd98dd296705415720fe6d90
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/LAHWV6fZwUk.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4ac56b866116af89339361f95c6b0fc473c2efb03f0518d1299db74d350070
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/Ls6qMcgpdlM.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e420627874e37f8033b64c37921488f5cace828bb8b06ec6aa165e83e5ac331b
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/M5sptjrboqA.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ac4f859ea522f39992217bdbd4c3eb67286e46a0b09f7930e2a2273d3014fd
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/NSyqj1DXZKg.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e074bea28f3578006949a3510c8b38bdd9615589b5206b774d79adbffea369cf
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/NzVg-cFQJbE.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6d941a7b50bc7df07e2f174f147f92b84db1fecf6baa8142edf3d51c3a6ab3
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/OOik9i9wrU8.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35adf8a866c82c9f4364c6637794842712a47a90d3a3396ba70acca3b3ece1d7
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/TC4mH6nACm8.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de011e8dcedf4fa6fdfb27a3b84c784ec91781d4199312e93b4d5761470ea0f
3
+ size 327788
latent_diffusion/my_configs/audioldm_original/val_213055_07-24-12:30_cfg_scale_3.5_ddim_200_n_cand_3/TkclVqlyKx4.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06bc3e4f4ae952341bc677556a4d205f7bc8ca1eddea6da15bd1f285aa95982
3
+ size 327788