Hugging Face's logo

nonoJDWAOIDAWKDA
/
Amelia5_ft_StyleTTS2

Text-to-Speech
English
StyleTTS2
speech-synthesis
Model card Files Community
nonoJDWAOIDAWKDA commited on
Commit
7abe5bb
·
verified ·
1 Parent(s): d3aa719

Upload StyleTTS2 checkpoint epoch_2nd_00004.pth with all inference components

Browse files
Files changed (14) hide show
  1. README.md +4 -4
  2. bert.pth +1 -1
  3. bert_encoder.pth +1 -1
  4. checkpoint.pth +1 -1
  5. config.json +3 -3
  6. decoder.pth +1 -1
  7. diffusion.pth +1 -1
  8. mpd.pth +1 -1
  9. msd.pth +1 -1
  10. predictor.pth +1 -1
  11. predictor_encoder.pth +1 -1
  12. style_encoder.pth +1 -1
  13. text_aligner.pth +1 -1
  14. text_encoder.pth +1 -1
README.md CHANGED
@@ -16,16 +16,16 @@ This model is a fine-tuned version of StyleTTS2, containing all necessary compon
16
  - **Base Model:** StyleTTS2-LibriTTS
17
  - **Architecture:** StyleTTS2
18
  - **Task:** Text-to-Speech
19
- - **Last Checkpoint:** epoch_2nd_00005.pth
20
 
21
  ## Training Details
22
  - **Total Epochs:** 6
23
- - **Completed Epochs:** 5
24
- - **Total Iterations:** 3852
25
  - **Batch Size:** 2
26
  - **Max Length:** 630
27
  - **Learning Rate:** 0.0001
28
- - **Final Validation Loss:** 0.457043
29
 
30
  ## Model Components
31
  The repository includes all necessary components for inference:
 
16
  - **Base Model:** StyleTTS2-LibriTTS
17
  - **Architecture:** StyleTTS2
18
  - **Task:** Text-to-Speech
19
+ - **Last Checkpoint:** epoch_2nd_00004.pth
20
 
21
  ## Training Details
22
  - **Total Epochs:** 6
23
+ - **Completed Epochs:** 4
24
+ - **Total Iterations:** 3210
25
  - **Batch Size:** 2
26
  - **Max Length:** 630
27
  - **Learning Rate:** 0.0001
28
+ - **Final Validation Loss:** 0.440237
29
 
30
  ## Model Components
31
  The repository includes all necessary components for inference:
bert.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee18941d8de0b38b55051042545eeed37d4acddcc145879304a595e9bd20fcc
3
  size 25178740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f455155e8d5da7b118fc7f242fc030f1c80352bdd7ffeadfd5d56100e34b2c
3
  size 25178740
bert_encoder.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f03ec495425448c9eead8d3bc6830fa7f041488fa7bd4da5afbd7e4caa7b463
3
  size 1576502
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516d0c26927c16252c82bc1ec8f4814ed3d0f1f87b7e9ce14e47b10c140f1b12
3
  size 1576502
checkpoint.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b06b45b5d3580e95f3b66c3593808551f419e154941a7ec3d575ea99f3d249c6
3
  size 2201837262
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6c901db1d412ab532e849b6188417d7752e61a91c4ade6fef74420e7c10df7
3
  size 2201837262
config.json CHANGED
@@ -112,9 +112,9 @@
112
  "val_data": "Data/val_list.txt"
113
  },
114
  "model_state": {
115
- "epoch": 5,
116
- "iterations": 3852,
117
- "val_loss": 0.4570428133010864
118
  },
119
  "training_metrics": {
120
  "train_loss": [],
 
112
  "val_data": "Data/val_list.txt"
113
  },
114
  "model_state": {
115
+ "epoch": 4,
116
+ "iterations": 3210,
117
+ "val_loss": 0.4402371048927307
118
  },
119
  "training_metrics": {
120
  "train_loss": [],
decoder.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1a612e6858efbe5275f646b9a99c131a70c9602072d02b48fe1b9b4af2a0c0
3
  size 217409318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1cb68b7a11b377c2735c3a14e9e79ddbb259e8de110ec727503b8250e370de
3
  size 217409318
diffusion.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c63929e1718bc3a2aa28ce057e725096b605ae35e63ee1fb2dec3ec5627e911b
3
  size 87699504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc96a5404905c3f091db8771de69c03c8a4cc1004e19b92e9539d33d6787e68b
3
  size 87699504
mpd.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ecab163aa500835a32ffe4ecca4736b1fc35a2bd1457d82baa6600adf301ca
3
  size 164447824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892d50728abffabbe7c6bf02201bc7c27291d63d32af7e440a18510a499e01c4
3
  size 164447824
msd.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:348c8b6490fe206ed1bab9af65b158f702fa35e48a47801d47477b497c8f77bc
3
  size 1139020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043ea7ff0690c1fd0ca8010853cfbbdb32e54215985b681fd756dc360f0edf3e
3
  size 1139020
predictor.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2c6b0d35d647ca44a8bab0fc5686269261ffb2964560d9214ae06a9123a5ee6
3
  size 64813639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1c678557fbc179d88bc8b4b8cecb5ec12f414ae1298d8d71933d8814644c19
3
  size 64813639
predictor_encoder.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae92d220966b75df923ecc44d82da782b118ecf3a71fc4dec521ea7773fa6d63
3
  size 55547155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f2e9bad7cb2ee4cb5b1d1fba60c2edba43fe8a951d783e39127daa15cc1def
3
  size 55547155
style_encoder.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b17085eb31b547d7ad27a649e646ac5bb67d4a50477357e3af555eda7dce9840
3
  size 55546871
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64160231f1dd8255f6557f0fef430a268a285dd283d42298af585b8595a20ab8
3
  size 55546871
text_aligner.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a653fa61a47b725c720da8f154f1039e62689112fe518476aa5e0e17d929443a
3
  size 31531315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e9755ee688eb06fb4ae88a543b6d5af3587991232bacb14d2d1b265e4707fe
3
  size 31531315
text_encoder.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29cf768cac0703a857a342ea3bd5b41a80f1b2bffad41dd478de8b274addc74d
3
  size 22432460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6bc58f7f138acc78211c25210dfadff386c86eb32b82944aaf8b523be92159
3
  size 22432460