nonoJDWAOIDAWKDA
commited on
Upload StyleTTS2 checkpoint epoch_2nd_00009.pth with all inference components
Browse files- README.md +5 -5
- bert.pth +1 -1
- bert_encoder.pth +1 -1
- checkpoint.pth +2 -2
- config.json +37 -49
- 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:** 120
|
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_00009.pth
|
20 |
|
21 |
## Training Details
|
22 |
+
- **Total Epochs:** 30
|
23 |
+
- **Completed Epochs:** 9
|
24 |
+
- **Total Iterations:** 774
|
25 |
- **Batch Size:** 2
|
26 |
- **Max Length:** 120
|
27 |
- **Learning Rate:** 0.0001
|
28 |
+
- **Final Validation Loss:** 0.422153
|
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 sha256:1413a5cdfa34300aed0fe9a718e19631cb65b632d9a672ac27ecffd0eb81675f
|
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:fffeaf7ea2ece022f6cc3abe7a40e902a60482e842ba4eaa5eb3a450fc0f6178
|
3 |
size 1576502
|
checkpoint.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b1e42a03ddeab22116f039e0b819312600e496dd6882e74909f063083431c7
|
3 |
+
size 2040092478
|
config.json
CHANGED
@@ -72,7 +72,7 @@
|
|
72 |
"style_dim": 128
|
73 |
},
|
74 |
"training_config": {
|
75 |
-
"epochs":
|
76 |
"batch_size": 2,
|
77 |
"max_len": 120,
|
78 |
"optimizer": {
|
@@ -112,62 +112,53 @@
|
|
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": [],
|
121 |
"val_loss": [
|
122 |
-
|
123 |
-
|
|
|
|
|
|
|
|
|
124 |
56.0,
|
125 |
-
50.0,
|
126 |
-
47.0,
|
127 |
-
54.0,
|
128 |
48.0,
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
8.0,
|
134 |
-
12.0,
|
135 |
-
19.0,
|
136 |
-
27.0
|
137 |
],
|
138 |
"dur_loss": [
|
139 |
-
0.
|
140 |
-
0.
|
141 |
-
0.
|
142 |
0.431,
|
143 |
-
0.
|
144 |
-
0.
|
145 |
-
0.
|
146 |
-
0.
|
147 |
-
0.
|
148 |
-
0.
|
149 |
-
0.
|
150 |
-
0.
|
151 |
-
0.428,
|
152 |
-
0.406,
|
153 |
-
0.413
|
154 |
],
|
155 |
"F0_loss": [
|
156 |
-
1.
|
|
|
|
|
|
|
|
|
|
|
157 |
1.218,
|
158 |
-
1.
|
159 |
-
1.
|
160 |
-
|
161 |
-
1.
|
162 |
-
1.
|
163 |
-
1.138,
|
164 |
-
1.081,
|
165 |
-
1.116,
|
166 |
-
1.159,
|
167 |
-
1.134,
|
168 |
-
1.042,
|
169 |
-
1.115,
|
170 |
-
1.204
|
171 |
],
|
172 |
"epochs": [
|
173 |
1,
|
@@ -181,10 +172,7 @@
|
|
181 |
9,
|
182 |
10,
|
183 |
11,
|
184 |
-
12
|
185 |
-
13,
|
186 |
-
14,
|
187 |
-
15
|
188 |
]
|
189 |
}
|
190 |
}
|
|
|
72 |
"style_dim": 128
|
73 |
},
|
74 |
"training_config": {
|
75 |
+
"epochs": 30,
|
76 |
"batch_size": 2,
|
77 |
"max_len": 120,
|
78 |
"optimizer": {
|
|
|
112 |
"val_data": "Data/val_list.txt"
|
113 |
},
|
114 |
"model_state": {
|
115 |
+
"epoch": 9,
|
116 |
+
"iterations": 774,
|
117 |
+
"val_loss": 0.4221532940864563
|
118 |
},
|
119 |
"training_metrics": {
|
120 |
"train_loss": [],
|
121 |
"val_loss": [
|
122 |
+
26.0,
|
123 |
+
21.0,
|
124 |
+
12.0,
|
125 |
+
5.0,
|
126 |
+
57.0,
|
127 |
+
4.0,
|
128 |
56.0,
|
|
|
|
|
|
|
129 |
48.0,
|
130 |
+
39.0,
|
131 |
+
34.0,
|
132 |
+
53.0,
|
133 |
+
2.0
|
|
|
|
|
|
|
|
|
134 |
],
|
135 |
"dur_loss": [
|
136 |
+
0.434,
|
137 |
+
0.481,
|
138 |
+
0.437,
|
139 |
0.431,
|
140 |
+
0.42,
|
141 |
+
0.43,
|
142 |
+
0.463,
|
143 |
+
0.436,
|
144 |
+
0.437,
|
145 |
+
0.422,
|
146 |
+
0.432,
|
147 |
+
0.425
|
|
|
|
|
|
|
148 |
],
|
149 |
"F0_loss": [
|
150 |
+
1.093,
|
151 |
+
1.175,
|
152 |
+
1.097,
|
153 |
+
1.123,
|
154 |
+
1.108,
|
155 |
+
1.183,
|
156 |
1.218,
|
157 |
+
1.246,
|
158 |
+
1.048,
|
159 |
+
0.998,
|
160 |
+
1.156,
|
161 |
+
1.026
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
],
|
163 |
"epochs": [
|
164 |
1,
|
|
|
172 |
9,
|
173 |
10,
|
174 |
11,
|
175 |
+
12
|
|
|
|
|
|
|
176 |
]
|
177 |
}
|
178 |
}
|
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 sha256:9d6eb7d149bfb8cf2a0d927f30df312371b72b00e7959c3e6f3d7371d574a0f2
|
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 sha256:69229a607b119bf2c180406e680c1e06acefc44ec4d51fe294040f5215cb8a68
|
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 sha256:7c84bd61e997bdd1adec21249172906274abfe395992735d202419000dd544c9
|
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:b9f48c1161e725906d25583784a23a49091934b0e73edd2b1a024bb077bcabfe
|
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:eafafa34fa9d2b4a9268382dadc4a844c3f7dd900faf86a36fab3170c0e6f7bf
|
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 sha256:3c92fae2c2b4fe19e8eb5c07176f9225a839e625e801acdcf0c16e22b75fe492
|
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 sha256:4ef0b741adf3b2b9b4e40cd4eaad7bfbd1ececb5681d72ded1f2ae0a09af6f1a
|
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:b8889fdb9194441fa54090c37b8d3e050a2d8904220c9db53bbef8f319c8cf25
|
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 sha256:66fcdb1d2c4fac5943dca1326132d637bec7eb42f93ee1bfd5c8ee580a161aee
|
3 |
size 22432460
|
training_metrics.png
CHANGED