nonoJDWAOIDAWKDA
commited on
Upload StyleTTS2 checkpoint epoch_2nd_00029.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 +128 -8
- 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:** 30
|
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_00029.pth
|
20 |
|
21 |
## Training Details
|
22 |
- **Total Epochs:** 30
|
23 |
+
- **Completed Epochs:** 29
|
24 |
+
- **Total Iterations:** 2341
|
25 |
- **Batch Size:** 2
|
26 |
+
- **Max Length:** 110
|
27 |
- **Learning Rate:** 0.0001
|
28 |
+
- **Final Validation Loss:** 0.405025
|
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 sha256:6158ffbde4828b5bd729e0d5d1f8759432bfdbf5f3923c7ac77ed88f1dad37ad
|
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:cb4c35a681712953ef701d4bedaa227908a5e5e57b20daa604649e6a293c7b1c
|
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 sha256:50a108ca11a998e804ad4898c6d9e220101e6ff6ac0ef7f7eeeb10433ac1e50e
|
3 |
+
size 2242747934
|
config.json
CHANGED
@@ -74,7 +74,7 @@
|
|
74 |
"training_config": {
|
75 |
"epochs": 30,
|
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": [],
|
@@ -130,7 +130,37 @@
|
|
130 |
39.0,
|
131 |
34.0,
|
132 |
53.0,
|
133 |
-
2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
],
|
135 |
"dur_loss": [
|
136 |
0.434,
|
@@ -144,7 +174,37 @@
|
|
144 |
0.437,
|
145 |
0.422,
|
146 |
0.432,
|
147 |
-
0.425
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
148 |
],
|
149 |
"F0_loss": [
|
150 |
1.093,
|
@@ -158,7 +218,37 @@
|
|
158 |
1.048,
|
159 |
0.998,
|
160 |
1.156,
|
161 |
-
1.026
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
],
|
163 |
"epochs": [
|
164 |
1,
|
@@ -172,7 +262,37 @@
|
|
172 |
9,
|
173 |
10,
|
174 |
11,
|
175 |
-
12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
176 |
]
|
177 |
}
|
178 |
}
|
|
|
74 |
"training_config": {
|
75 |
"epochs": 30,
|
76 |
"batch_size": 2,
|
77 |
+
"max_len": 110,
|
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": 29,
|
116 |
+
"iterations": 2341,
|
117 |
+
"val_loss": 0.40502485632896423
|
118 |
},
|
119 |
"training_metrics": {
|
120 |
"train_loss": [],
|
|
|
130 |
39.0,
|
131 |
34.0,
|
132 |
53.0,
|
133 |
+
2.0,
|
134 |
+
5.0,
|
135 |
+
50.0,
|
136 |
+
38.0,
|
137 |
+
26.0,
|
138 |
+
13.0,
|
139 |
+
13.0,
|
140 |
+
2.0,
|
141 |
+
49.0,
|
142 |
+
37.0,
|
143 |
+
23.0,
|
144 |
+
41.0,
|
145 |
+
40.0,
|
146 |
+
42.0,
|
147 |
+
41.0,
|
148 |
+
39.0,
|
149 |
+
58.0,
|
150 |
+
55.0,
|
151 |
+
54.0,
|
152 |
+
51.0,
|
153 |
+
50.0,
|
154 |
+
3.0,
|
155 |
+
1.0,
|
156 |
+
0.0,
|
157 |
+
5.0,
|
158 |
+
3.0,
|
159 |
+
41.0,
|
160 |
+
39.0,
|
161 |
+
35.0,
|
162 |
+
32.0,
|
163 |
+
30.0
|
164 |
],
|
165 |
"dur_loss": [
|
166 |
0.434,
|
|
|
174 |
0.437,
|
175 |
0.422,
|
176 |
0.432,
|
177 |
+
0.425,
|
178 |
+
0.456,
|
179 |
+
0.462,
|
180 |
+
0.45,
|
181 |
+
0.427,
|
182 |
+
0.456,
|
183 |
+
0.428,
|
184 |
+
0.438,
|
185 |
+
0.422,
|
186 |
+
0.428,
|
187 |
+
0.432,
|
188 |
+
0.44,
|
189 |
+
0.423,
|
190 |
+
0.431,
|
191 |
+
0.449,
|
192 |
+
0.414,
|
193 |
+
0.427,
|
194 |
+
0.447,
|
195 |
+
0.45,
|
196 |
+
0.435,
|
197 |
+
0.428,
|
198 |
+
0.426,
|
199 |
+
0.417,
|
200 |
+
0.425,
|
201 |
+
0.434,
|
202 |
+
0.412,
|
203 |
+
0.415,
|
204 |
+
0.422,
|
205 |
+
0.398,
|
206 |
+
0.416,
|
207 |
+
0.405
|
208 |
],
|
209 |
"F0_loss": [
|
210 |
1.093,
|
|
|
218 |
1.048,
|
219 |
0.998,
|
220 |
1.156,
|
221 |
+
1.026,
|
222 |
+
1.196,
|
223 |
+
1.173,
|
224 |
+
1.148,
|
225 |
+
1.264,
|
226 |
+
1.266,
|
227 |
+
1.115,
|
228 |
+
1.089,
|
229 |
+
1.103,
|
230 |
+
1.178,
|
231 |
+
1.108,
|
232 |
+
1.106,
|
233 |
+
1.151,
|
234 |
+
1.217,
|
235 |
+
1.187,
|
236 |
+
1.04,
|
237 |
+
1.111,
|
238 |
+
1.17,
|
239 |
+
1.195,
|
240 |
+
1.087,
|
241 |
+
1.144,
|
242 |
+
1.121,
|
243 |
+
1.18,
|
244 |
+
1.206,
|
245 |
+
1.125,
|
246 |
+
1.101,
|
247 |
+
1.072,
|
248 |
+
1.099,
|
249 |
+
1.223,
|
250 |
+
1.188,
|
251 |
+
1.097
|
252 |
],
|
253 |
"epochs": [
|
254 |
1,
|
|
|
262 |
9,
|
263 |
10,
|
264 |
11,
|
265 |
+
12,
|
266 |
+
13,
|
267 |
+
14,
|
268 |
+
15,
|
269 |
+
16,
|
270 |
+
17,
|
271 |
+
18,
|
272 |
+
19,
|
273 |
+
20,
|
274 |
+
21,
|
275 |
+
22,
|
276 |
+
23,
|
277 |
+
24,
|
278 |
+
25,
|
279 |
+
26,
|
280 |
+
27,
|
281 |
+
28,
|
282 |
+
29,
|
283 |
+
30,
|
284 |
+
31,
|
285 |
+
32,
|
286 |
+
33,
|
287 |
+
34,
|
288 |
+
35,
|
289 |
+
36,
|
290 |
+
37,
|
291 |
+
38,
|
292 |
+
39,
|
293 |
+
40,
|
294 |
+
41,
|
295 |
+
42
|
296 |
]
|
297 |
}
|
298 |
}
|
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 sha256:815400ba8f1bd08fd28db9ef9330ef2be5d5cac52224fd6d0914864831ae1102
|
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:bae1a9abccdb586c140a4c65231a7cc97766e8fbd9bb20e7b261ff7e2439baf0
|
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 sha256:8ff78d274d70254f641c679ec166a7b664ef91710a7fce8f69538b493a6d69da
|
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 sha256:2ddda48ce7bd021ebe7256cfe613cf17f69aba81c355cf6a37f36c6680956737
|
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:c01733aea2d2835e5ecfc8afe7ec1691bc8aaa0e651bc78d5dfdbe2cc028d556
|
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:ccbce2062e8de35c1e925ffa808b7f18790cb4a35370d324b3782829768fa478
|
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 sha256:9bff0b6024b314cf39d629322e025f324872b77621e7eff3e4083359156ad64e
|
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 sha256:4efc44b688aa089711691b7fae48767d3b8f461e519d749a5ed938d95b24a89c
|
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:ce4cf0da486560c3370a74f2a06a9d025c61d2361d6a54bedea7b6b302455784
|
3 |
size 22432460
|
training_metrics.png
CHANGED