Hugging Face's logo

SirAB
/
styletts2_finetune

TensorBoard
Model card Files
xet
Metrics Community
SirAB commited on
Commit
1fcaa7b
·
verified ·
1 Parent(s): 5c9433a

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. .gitattributes +26 -0
  2. LJSpeech2/config.yml +3 -3
  3. LJSpeech2/epoch_2nd_00070.pth +3 -0
  4. LJSpeech2/epoch_2nd_00094.wav +3 -0
  5. LJSpeech2/epoch_2nd_00095.wav +3 -0
  6. LJSpeech2/epoch_2nd_00096.wav +3 -0
  7. LJSpeech2/epoch_2nd_00097.wav +3 -0
  8. LJSpeech2/epoch_2nd_00098.wav +3 -0
  9. LJSpeech2/epoch_2nd_00099.wav +3 -0
  10. LJSpeech2/epoch_2nd_00100.wav +3 -0
  11. LJSpeech2/epoch_2nd_00101.wav +3 -0
  12. LJSpeech2/epoch_2nd_00102.wav +3 -0
  13. LJSpeech2/epoch_2nd_00103.wav +3 -0
  14. LJSpeech2/epoch_2nd_00104.wav +3 -0
  15. LJSpeech2/epoch_2nd_00105.wav +3 -0
  16. LJSpeech2/epoch_2nd_00106.wav +3 -0
  17. LJSpeech2/epoch_2nd_00107.wav +3 -0
  18. LJSpeech2/epoch_2nd_00108.wav +3 -0
  19. LJSpeech2/epoch_2nd_00109.wav +3 -0
  20. LJSpeech2/epoch_2nd_00110.wav +3 -0
  21. LJSpeech2/epoch_2nd_00111.wav +3 -0
  22. LJSpeech2/epoch_2nd_00112.wav +3 -0
  23. LJSpeech2/epoch_2nd_00113.wav +3 -0
  24. LJSpeech2/epoch_2nd_00114.wav +3 -0
  25. LJSpeech2/epoch_2nd_00115.wav +3 -0
  26. LJSpeech2/epoch_2nd_00116.wav +3 -0
  27. LJSpeech2/epoch_2nd_00117.wav +3 -0
  28. LJSpeech2/epoch_2nd_00118.wav +3 -0
  29. LJSpeech2/epoch_2nd_00119.wav +3 -0
  30. LJSpeech2/tensorboard/events.out.tfevents.1744524923.23abfb24de6e.3515.0 +3 -0
  31. LJSpeech2/tensorboard/events.out.tfevents.1744524997.23abfb24de6e.3856.0 +3 -0
  32. LJSpeech2/tensorboard/events.out.tfevents.1744525072.23abfb24de6e.4190.0 +3 -0
  33. LJSpeech2/tensorboard/events.out.tfevents.1744525277.23abfb24de6e.5054.0 +3 -0
  34. LJSpeech2/tensorboard/events.out.tfevents.1744525835.23abfb24de6e.7344.0 +3 -0
  35. LJSpeech2/train.log +0 -0
.gitattributes CHANGED
@@ -116,3 +116,29 @@ LJSpeech2/epoch_2nd_00090.wav filter=lfs diff=lfs merge=lfs -text
116
  LJSpeech2/epoch_2nd_00091.wav filter=lfs diff=lfs merge=lfs -text
117
  LJSpeech2/epoch_2nd_00092.wav filter=lfs diff=lfs merge=lfs -text
118
  LJSpeech2/epoch_2nd_00093.wav filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  LJSpeech2/epoch_2nd_00091.wav filter=lfs diff=lfs merge=lfs -text
117
  LJSpeech2/epoch_2nd_00092.wav filter=lfs diff=lfs merge=lfs -text
118
  LJSpeech2/epoch_2nd_00093.wav filter=lfs diff=lfs merge=lfs -text
119
+ LJSpeech2/epoch_2nd_00094.wav filter=lfs diff=lfs merge=lfs -text
120
+ LJSpeech2/epoch_2nd_00095.wav filter=lfs diff=lfs merge=lfs -text
121
+ LJSpeech2/epoch_2nd_00096.wav filter=lfs diff=lfs merge=lfs -text
122
+ LJSpeech2/epoch_2nd_00097.wav filter=lfs diff=lfs merge=lfs -text
123
+ LJSpeech2/epoch_2nd_00098.wav filter=lfs diff=lfs merge=lfs -text
124
+ LJSpeech2/epoch_2nd_00099.wav filter=lfs diff=lfs merge=lfs -text
125
+ LJSpeech2/epoch_2nd_00100.wav filter=lfs diff=lfs merge=lfs -text
126
+ LJSpeech2/epoch_2nd_00101.wav filter=lfs diff=lfs merge=lfs -text
127
+ LJSpeech2/epoch_2nd_00102.wav filter=lfs diff=lfs merge=lfs -text
128
+ LJSpeech2/epoch_2nd_00103.wav filter=lfs diff=lfs merge=lfs -text
129
+ LJSpeech2/epoch_2nd_00104.wav filter=lfs diff=lfs merge=lfs -text
130
+ LJSpeech2/epoch_2nd_00105.wav filter=lfs diff=lfs merge=lfs -text
131
+ LJSpeech2/epoch_2nd_00106.wav filter=lfs diff=lfs merge=lfs -text
132
+ LJSpeech2/epoch_2nd_00107.wav filter=lfs diff=lfs merge=lfs -text
133
+ LJSpeech2/epoch_2nd_00108.wav filter=lfs diff=lfs merge=lfs -text
134
+ LJSpeech2/epoch_2nd_00109.wav filter=lfs diff=lfs merge=lfs -text
135
+ LJSpeech2/epoch_2nd_00110.wav filter=lfs diff=lfs merge=lfs -text
136
+ LJSpeech2/epoch_2nd_00111.wav filter=lfs diff=lfs merge=lfs -text
137
+ LJSpeech2/epoch_2nd_00112.wav filter=lfs diff=lfs merge=lfs -text
138
+ LJSpeech2/epoch_2nd_00113.wav filter=lfs diff=lfs merge=lfs -text
139
+ LJSpeech2/epoch_2nd_00114.wav filter=lfs diff=lfs merge=lfs -text
140
+ LJSpeech2/epoch_2nd_00115.wav filter=lfs diff=lfs merge=lfs -text
141
+ LJSpeech2/epoch_2nd_00116.wav filter=lfs diff=lfs merge=lfs -text
142
+ LJSpeech2/epoch_2nd_00117.wav filter=lfs diff=lfs merge=lfs -text
143
+ LJSpeech2/epoch_2nd_00118.wav filter=lfs diff=lfs merge=lfs -text
144
+ LJSpeech2/epoch_2nd_00119.wav filter=lfs diff=lfs merge=lfs -text
LJSpeech2/config.yml CHANGED
@@ -1,11 +1,11 @@
1
  {ASR_config: Utils/ASR/config.yml, ASR_path: Utils/ASR/epoch_00080.pth, F0_path: Utils/JDC/bst.t7,
2
  PLBERT_dir: Utils/PLBERT/, batch_size: 2, data_params: {OOD_data: Data/OOD_texts.txt,
3
  min_length: 50, root_path: /content/StyleTTS2/Dataset, train_data: Data/train_list.txt,
4
- val_data: Data/val_list.txt}, device: cuda, epochs_1st: 20, epochs_2nd: 100, first_stage_path: first_stage.pth,
5
  load_only_params: false, log_dir: Models/LJSpeech, log_interval: 10, loss_params: {
6
  TMA_epoch: 10000, diff_epoch: 0, joint_epoch: 0, lambda_F0: 1.0, lambda_ce: 20.0,
7
  lambda_diff: 1.0, lambda_dur: 1.0, lambda_gen: 1.0, lambda_mel: 5.0, lambda_mono: 1.0,
8
- lambda_norm: 1.0, lambda_s2s: 1.0, lambda_slm: 1.0, lambda_sty: 1.0}, max_len: 400,
9
  model_params: {decoder: {gen_istft_hop_size: 5, gen_istft_n_fft: 20, resblock_dilation_sizes: [
10
  [1, 3, 5], [1, 3, 5], [1, 3, 5]], resblock_kernel_sizes: [3, 7, 11], type: istftnet,
11
  upsample_initial_channel: 512, upsample_kernel_sizes: [20, 12], upsample_rates: [
@@ -16,6 +16,6 @@
16
  slm: {hidden: 768, initial_channel: 64, model: microsoft/wavlm-base-plus, nlayers: 13,
17
  sr: 16000}, style_dim: 128}, optimizer_params: {bert_lr: 1.0e-05, ft_lr: 1.0e-05,
18
  lr: 0.0001}, preprocess_params: {spect_params: {hop_length: 300, n_fft: 2048,
19
- win_length: 1200}, sr: 24000}, pretrained_model: LJSpeech2/epoch_2nd_00068.pth,
20
  save_freq: 1, second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5,
21
  iter: 10, max_len: 500, min_len: 400, scale: 0.01, sig: 1.5, thresh: 5}}
 
1
  {ASR_config: Utils/ASR/config.yml, ASR_path: Utils/ASR/epoch_00080.pth, F0_path: Utils/JDC/bst.t7,
2
  PLBERT_dir: Utils/PLBERT/, batch_size: 2, data_params: {OOD_data: Data/OOD_texts.txt,
3
  min_length: 50, root_path: /content/StyleTTS2/Dataset, train_data: Data/train_list.txt,
4
+ val_data: Data/val_list.txt}, device: cuda, epochs_1st: 20, epochs_2nd: 200, first_stage_path: first_stage.pth,
5
  load_only_params: false, log_dir: Models/LJSpeech, log_interval: 10, loss_params: {
6
  TMA_epoch: 10000, diff_epoch: 0, joint_epoch: 0, lambda_F0: 1.0, lambda_ce: 20.0,
7
  lambda_diff: 1.0, lambda_dur: 1.0, lambda_gen: 1.0, lambda_mel: 5.0, lambda_mono: 1.0,
8
+ lambda_norm: 1.0, lambda_s2s: 1.0, lambda_slm: 1.0, lambda_sty: 1.0}, max_len: 430,
9
  model_params: {decoder: {gen_istft_hop_size: 5, gen_istft_n_fft: 20, resblock_dilation_sizes: [
10
  [1, 3, 5], [1, 3, 5], [1, 3, 5]], resblock_kernel_sizes: [3, 7, 11], type: istftnet,
11
  upsample_initial_channel: 512, upsample_kernel_sizes: [20, 12], upsample_rates: [
 
16
  slm: {hidden: 768, initial_channel: 64, model: microsoft/wavlm-base-plus, nlayers: 13,
17
  sr: 16000}, style_dim: 128}, optimizer_params: {bert_lr: 1.0e-05, ft_lr: 1.0e-05,
18
  lr: 0.0001}, preprocess_params: {spect_params: {hop_length: 300, n_fft: 2048,
19
+ win_length: 1200}, sr: 24000}, pretrained_model: LJSpeech2/epoch_2nd_00069.pth,
20
  save_freq: 1, second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5,
21
  iter: 10, max_len: 500, min_len: 400, scale: 0.01, sig: 1.5, thresh: 5}}
LJSpeech2/epoch_2nd_00070.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb2b3cd917ad1d90654c3f79583a430f30006793acf595c37e1815b5a6db101
3
+ size 1217204553
LJSpeech2/epoch_2nd_00094.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d262379d7ec1d59d4b0bf67348f00571724a37cf9f167eb378d76ae7d0b7fa1b
3
+ size 785944
LJSpeech2/epoch_2nd_00095.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0eda59c60c0703ec1ac7212207f766472754d5cab996faacbf9e9a81e5b558
3
+ size 835144
LJSpeech2/epoch_2nd_00096.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf029d6d4c73d22042c81369dc8601d7692cb2c5729bfb904875290178914b26
3
+ size 769144
LJSpeech2/epoch_2nd_00097.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6252fa78f1859c4680434980ee61e5317e513e9a988758cb1baf6d8e909724
3
+ size 843544
LJSpeech2/epoch_2nd_00098.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0c6f9611aa50c7d8d74b95e5ec16217a5761a72dc40849f2dfb77182e11129
3
+ size 800344
LJSpeech2/epoch_2nd_00099.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7d148e63f66f153bc681e8a8892fce1ce72e285e47e1ff8979410b59b4947e
3
+ size 863944
LJSpeech2/epoch_2nd_00100.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbbaf4f2eff60ee3eaddf10d2fc5e33cffcb2746894d2484685251c307df286
3
+ size 797944
LJSpeech2/epoch_2nd_00101.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9116521c57184628c61f1ad88e3a013d9f45bb8b8fa7123fe36d51de2e772b4f
3
+ size 861544
LJSpeech2/epoch_2nd_00102.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7259f9608ab7962da30b6438665c029b2768452799f5773443cd7f9697cf2465
3
+ size 835144
LJSpeech2/epoch_2nd_00103.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8b875a7a7d1e1ea736f640fe56043f5050a2bd28f9fd75113f0c4753f331ff
3
+ size 862744
LJSpeech2/epoch_2nd_00104.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c050659dd767bfee8c4ee6fbbf318d0ac3f5f1273547fa36cbefd92e61f2f8e
3
+ size 897544
LJSpeech2/epoch_2nd_00105.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124c8b0b12d7fba17e3ee6f29632e265cd12b6b29b6af9e781372b262881dadc
3
+ size 850744
LJSpeech2/epoch_2nd_00106.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6027244b8aeca68daa90ca7a4ffcab8e525ab5bcbeb4fcd333e8ae6e6b08e763
3
+ size 865144
LJSpeech2/epoch_2nd_00107.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b0ef732a995f2ee030cfd0e49b10c1836c599bc23a7e2b38f7753b46f03d1c
3
+ size 824344
LJSpeech2/epoch_2nd_00108.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf24bd9d6646157895ee6321dc60685643185ee44a0c73b6a91bd13ae4aaa7a
3
+ size 751144
LJSpeech2/epoch_2nd_00109.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5414dd8c525192775137f19428c741186c0b51b10623bbf04c178a044257e31b
3
+ size 826744
LJSpeech2/epoch_2nd_00110.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bea1f30dba6f99dadc4f2b7ff7ec3cb65d783af16959a9acd39270a649fe92b
3
+ size 812344
LJSpeech2/epoch_2nd_00111.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b15f225d69f7f44a4e3c70b5a469b0d0e5073d4359c0590897fdf8beabafdb
3
+ size 825544
LJSpeech2/epoch_2nd_00112.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44001f6d7527e2947d8b6eb2e4abd4868adc9da2368c5b5cbf6b028fafc7811a
3
+ size 861544
LJSpeech2/epoch_2nd_00113.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26772d1a7e099536648e79f65ff3b27b7a64679d0cbb2ee526071c40c673beae
3
+ size 860344
LJSpeech2/epoch_2nd_00114.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f4bd1f8a7d9e433be232ab5004eca25bbcb75a0a81f0e555834c2be8dc7b83
3
+ size 849544
LJSpeech2/epoch_2nd_00115.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c0930c2c6deadd2dac4a46c702b8762d356d6ebc92be0df053d0924a612d24
3
+ size 871144
LJSpeech2/epoch_2nd_00116.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1635d16cc1a106c6a01b33e54a0cfc6fd94db856f54ec70d994d35d248e918d
3
+ size 847144
LJSpeech2/epoch_2nd_00117.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8482d1271978478affc8c658007adc4914cf8fac8808b53c42b4d3f9ae8ba6c1
3
+ size 867544
LJSpeech2/epoch_2nd_00118.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9189ae85ae24c64711af337d96562f0c3ad9bd848f42621bf2a8c80e49d606
3
+ size 837544
LJSpeech2/epoch_2nd_00119.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfc0a543075f39d3bb2c0f88d01afd4d295faf1244d7c20783e7fa9363cb102
3
+ size 860344
LJSpeech2/tensorboard/events.out.tfevents.1744524923.23abfb24de6e.3515.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffacd14dcb7a7f90df7e54c84c8d4b62736a4c067d8e3d9c3568eef1fcb88a11
3
+ size 88
LJSpeech2/tensorboard/events.out.tfevents.1744524997.23abfb24de6e.3856.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7639d60bcdf50a51b0e197f027e4735b8ea060c117ccccca830591ab66a83755
3
+ size 88
LJSpeech2/tensorboard/events.out.tfevents.1744525072.23abfb24de6e.4190.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b2da6f8a1f58f9cfc4d2ea83099a2ab11340640a5fe8367bbcaa55b176c577
3
+ size 1972
LJSpeech2/tensorboard/events.out.tfevents.1744525277.23abfb24de6e.5054.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40d3a0825178adcf8f471431fd6a3ffd96a43cecb5a8bdf53173587123d459f
3
+ size 1972
LJSpeech2/tensorboard/events.out.tfevents.1744525835.23abfb24de6e.7344.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cb5eb5e28eecc36942db0e75df4fb96e696bc060d8c16ad4f12e2fd4b62e73
3
+ size 167624
LJSpeech2/train.log CHANGED
The diff for this file is too large to render. See raw diff