nonoJDWAOIDAWKDA
commited on
Upload StyleTTS2 checkpoint epoch_2nd_00003.pth with all inference components
Browse files- README.md +6 -6
- bert.pth +1 -1
- bert_encoder.pth +1 -1
- checkpoint.pth +1 -1
- config.json +29 -9
- decoder.pth +1 -1
- diffusion.pth +1 -1
- mpd.pth +1 -1
- msd.pth +1 -1
- predictor.pth +1 -1
- predictor_encoder.pth +1 -1
- style_encoder.pth +1 -1
- text_aligner.pth +1 -1
- text_encoder.pth +1 -1
- training_metrics.png +0 -0
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:**
|
20 |
|
21 |
## Training Details
|
22 |
-
- **Total Epochs:**
|
23 |
-
- **Completed Epochs:**
|
24 |
-
- **Total Iterations:**
|
25 |
- **Batch Size:** 2
|
26 |
-
- **Max Length:**
|
27 |
- **Learning Rate:** 0.0001
|
28 |
-
- **Final Validation Loss:** 0.
|
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_00003.pth
|
20 |
|
21 |
## Training Details
|
22 |
+
- **Total Epochs:** 5
|
23 |
+
- **Completed Epochs:** 3
|
24 |
+
- **Total Iterations:** 3384
|
25 |
- **Batch Size:** 2
|
26 |
+
- **Max Length:** 600
|
27 |
- **Learning Rate:** 0.0001
|
28 |
+
- **Final Validation Loss:** 0.399824
|
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:
|
3 |
size 25178740
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8547df3d46173d36f32153f6f5d0536a98bd9cd06ac53026946ff89dafdbf5d
|
3 |
size 25178740
|
bert_encoder.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1576502
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51a5c0ae501ee18c60230d9194c1666312297aab3f56961968ba1915efe81e95
|
3 |
size 1576502
|
checkpoint.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2242747934
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4867d7892552a55810009454aa79bed07670a40e5ebc03e3d1f1848fc3650f5b
|
3 |
size 2242747934
|
config.json
CHANGED
@@ -72,9 +72,9 @@
|
|
72 |
"style_dim": 128
|
73 |
},
|
74 |
"training_config": {
|
75 |
-
"epochs":
|
76 |
"batch_size": 2,
|
77 |
-
"max_len":
|
78 |
"optimizer": {
|
79 |
"bert_lr": 1e-05,
|
80 |
"ft_lr": 0.0001,
|
@@ -112,9 +112,9 @@
|
|
112 |
"val_data": "Data/val_list.txt"
|
113 |
},
|
114 |
"model_state": {
|
115 |
-
"epoch":
|
116 |
-
"iterations":
|
117 |
-
"val_loss": 0.
|
118 |
},
|
119 |
"training_metrics": {
|
120 |
"train_loss": [],
|
@@ -135,7 +135,12 @@
|
|
135 |
29.0,
|
136 |
11.0,
|
137 |
52.0,
|
138 |
-
48.0
|
|
|
|
|
|
|
|
|
|
|
139 |
],
|
140 |
"dur_loss": [
|
141 |
0.44,
|
@@ -154,7 +159,12 @@
|
|
154 |
0.399,
|
155 |
0.409,
|
156 |
0.397,
|
157 |
-
0.408
|
|
|
|
|
|
|
|
|
|
|
158 |
],
|
159 |
"F0_loss": [
|
160 |
2.865,
|
@@ -173,7 +183,12 @@
|
|
173 |
2.515,
|
174 |
2.663,
|
175 |
2.66,
|
176 |
-
2.477
|
|
|
|
|
|
|
|
|
|
|
177 |
],
|
178 |
"epochs": [
|
179 |
1,
|
@@ -192,7 +207,12 @@
|
|
192 |
14,
|
193 |
15,
|
194 |
16,
|
195 |
-
17
|
|
|
|
|
|
|
|
|
|
|
196 |
]
|
197 |
}
|
198 |
}
|
|
|
72 |
"style_dim": 128
|
73 |
},
|
74 |
"training_config": {
|
75 |
+
"epochs": 5,
|
76 |
"batch_size": 2,
|
77 |
+
"max_len": 600,
|
78 |
"optimizer": {
|
79 |
"bert_lr": 1e-05,
|
80 |
"ft_lr": 0.0001,
|
|
|
112 |
"val_data": "Data/val_list.txt"
|
113 |
},
|
114 |
"model_state": {
|
115 |
+
"epoch": 3,
|
116 |
+
"iterations": 3384,
|
117 |
+
"val_loss": 0.39982396364212036
|
118 |
},
|
119 |
"training_metrics": {
|
120 |
"train_loss": [],
|
|
|
135 |
29.0,
|
136 |
11.0,
|
137 |
52.0,
|
138 |
+
48.0,
|
139 |
+
18.0,
|
140 |
+
5.0,
|
141 |
+
4.0,
|
142 |
+
57.0,
|
143 |
+
9.0
|
144 |
],
|
145 |
"dur_loss": [
|
146 |
0.44,
|
|
|
159 |
0.399,
|
160 |
0.409,
|
161 |
0.397,
|
162 |
+
0.408,
|
163 |
+
0.432,
|
164 |
+
0.404,
|
165 |
+
0.406,
|
166 |
+
0.4,
|
167 |
+
0.403
|
168 |
],
|
169 |
"F0_loss": [
|
170 |
2.865,
|
|
|
183 |
2.515,
|
184 |
2.663,
|
185 |
2.66,
|
186 |
+
2.477,
|
187 |
+
1.751,
|
188 |
+
1.739,
|
189 |
+
1.76,
|
190 |
+
1.691,
|
191 |
+
1.72
|
192 |
],
|
193 |
"epochs": [
|
194 |
1,
|
|
|
207 |
14,
|
208 |
15,
|
209 |
16,
|
210 |
+
17,
|
211 |
+
18,
|
212 |
+
19,
|
213 |
+
20,
|
214 |
+
21,
|
215 |
+
22
|
216 |
]
|
217 |
}
|
218 |
}
|
decoder.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 217409318
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8385ec0be347a4251cddfd7391ac2e3a468c77967caddb023f13d5c5d2232343
|
3 |
size 217409318
|
diffusion.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 101337326
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8324d4c337027ced9ac87fe0018ff90cb74fa8d2652ea6cdf2a9d3f0ed232a3f
|
3 |
size 101337326
|
mpd.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 164447824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7cc86c797abefbcb2b5f60c8f5416f5366d1bbde05c203d5828266655fe974
|
3 |
size 164447824
|
msd.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1139020
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19d2b444de08e4e33b867114da66af862cc9a20f3ee2778a147bf4689395f15d
|
3 |
size 1139020
|
predictor.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64813639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7fcdf269e32fe125ca2bc3095a4c8a591b1034d886ccbcc7bc6cc808722cacc
|
3 |
size 64813639
|
predictor_encoder.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 55547155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef15e2dcf88df69ec0e3b324f481de2c1b387c047e0a2375ab9219b924594aca
|
3 |
size 55547155
|
style_encoder.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 55546871
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66f099fbedb7cd0cc47fa849f9efa2bd076a70285fd36062ed89b97725d2ce03
|
3 |
size 55546871
|
text_aligner.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31531315
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e8d32afb6ff2248713b03d1e73d5fbe6ada4f50be8575e86fb537a189f9d080
|
3 |
size 31531315
|
text_encoder.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22432460
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11cad4fab0fd34170fdd88a62129dac783dbd25eedaba045a65f2d760030462a
|
3 |
size 22432460
|
training_metrics.png
CHANGED