Upload StyleTTS2 checkpoint epoch_2nd_00005.pth with all inference components

README.md

@@ -16,16 +16,16 @@ This model is a fine-tuned version of StyleTTS2, containing all necessary compon
 - **Base Model:** StyleTTS2-LibriTTS
 - **Architecture:** StyleTTS2
 - **Task:** Text-to-Speech
-- **Last Checkpoint:** epoch_2nd_00001.pth
+- **Last Checkpoint:** epoch_2nd_00005.pth
 
 ## Training Details
 - **Total Epochs:** 6
-- **Completed Epochs:** 1
-- **Total Iterations:** 648
+- **Completed Epochs:** 5
+- **Total Iterations:** 1944
 - **Batch Size:** 2
-- **Max Length:** 630
+- **Max Length:** 620
 - **Learning Rate:** 0.0001
-- **Final Validation Loss:** 0.488410
+- **Final Validation Loss:** 0.485287
 
 ## Model Components
 The repository includes all necessary components for inference:

bert.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b086f44bf311f585cf073a52518c20095ba3c090be5af2847f23c976395ce3c
+oid sha256:ae20fea5f2d0c5aba00d867f1ed9241e7dc164811917ab06628b1faf65cc4c91
 size 25178740

bert_encoder.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba91ded085853bef041882bedfd28074284af14ebaa3e31ce8826987de729303
+oid sha256:31ba9acf684366042536f950897fd51cf210884cedfb27f94498b4859269aff4
 size 1576502

checkpoint.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ef7d7e768fecec6721c5545482b2896bf18a35e782e32bc9501d5b695989ad
-size 2026454778
+oid sha256:15f22f7d0b4ebd58ab444ed4e44ff9b9402d36c8b42b9364ecee857cafae75ed
+size 2201837262

config.json

@@ -74,7 +74,7 @@
   "training_config": {
     "epochs": 6,
     "batch_size": 2,
-    "max_len": 630,
+    "max_len": 620,
     "optimizer": {
       "bert_lr": 1e-05,
       "ft_lr": 0.0001,
@@ -112,9 +112,9 @@
     "val_data": "Data/val_list.txt"
   },
   "model_state": {
-    "epoch": 1,
-    "iterations": 648,
-    "val_loss": 0.48840951919555664
+    "epoch": 5,
+    "iterations": 1944,
+    "val_loss": 0.48528674244880676
   },
   "training_metrics": {
     "train_loss": [],
@@ -162,7 +162,13 @@
       42.0,
       16.0,
       5.0,
-      35.0
+      35.0,
+      13.0,
+      51.0,
+      4.0,
+      27.0,
+      44.0,
+      16.0
     ],
     "dur_loss": [
       0.502,
@@ -208,7 +214,13 @@
       0.445,
       0.439,
       0.524,
-      0.488
+      0.488,
+      0.495,
+      0.486,
+      0.488,
+      0.494,
+      0.484,
+      0.485
     ],
     "F0_loss": [
       1.759,
@@ -254,7 +266,13 @@
       1.443,
       1.441,
       1.573,
-      1.585
+      1.585,
+      1.659,
+      1.654,
+      1.68,
+      1.614,
+      1.596,
+      1.552
     ],
     "epochs": [
       1,
@@ -300,7 +318,13 @@
       41,
       42,
       43,
-      44
+      44,
+      45,
+      46,
+      47,
+      48,
+      49,
+      50
     ]
   }
 }

decoder.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1785d4f41b6cea59ac0830c67d43f9c5a0d91df94f218ac6f4682839b87432da
+oid sha256:a309dff51e689b9cd56001575287ab933de233e7ca777c8ffd6da77dac83da63
 size 217409318

diffusion.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf771d99fcfdfab7e0c2c905813f6846829d465b7167da29dbbbc267d4793af
+oid sha256:bee50db80c722cf72dfc28ce53bd8be86df7bd9d13ae56350587ac89bcc3c97b
 size 87699504

mpd.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62deedbbc57b8bc824a2d0f7765ce106fd58344f7bedbb4c6d93a31d8908f7f
+oid sha256:a59c4b2d4bdaa05a9b64f5b3d67fac6e06dfa91cc2e649f7107ea172a3f50a0e
 size 164447824

msd.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdad23273ae36500d80a90f4ffdf172b145dbb1f2384b1a92b8d470e881d6b53
+oid sha256:85130e48dedb76fa77ece85eea6f7f35420c40e8ff4e894f02ca2c7451d659e6
 size 1139020

predictor.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e5b9ef7a2ac2c286317b86b1626098f8abbe9ad9b2b3caa638711435e10755
+oid sha256:44d1eb7b58570cc0137e4e77a9b2f9cf7c9e0a0a28fb79eea13c0916c12a3e0f
 size 64813639

predictor_encoder.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a28c748d50e14bd662beaecb6a60682559fb6de5778ad5c614fe1fdda7e9bc
+oid sha256:87dd4dd75a97524c1e8fbf8731b91f1e20d9e8546e4b256ccc1fc651941a2a5d
 size 55547155

style_encoder.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b5682a776988c64de0a5d53c7e55f7ac05692cda6006f6596b1648681842f5
+oid sha256:3df89b7cbde89bbc338a27f5688e665bb765dbf80cf1f85135f356d90e36db07
 size 55546871

text_aligner.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ee1d58f1389f969a8035ba762ae656005b2dff7278c87ab59dbcd60a28f448
+oid sha256:c3391b0d11ea3cb9e79f17e111fbcac63f7e6e0c192239332fc625ada4b43ba6
 size 31531315

text_encoder.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4817057f30f702acbeae12cac5c0ad3611cd32d62e9ca05e842aaa60e7c35b
+oid sha256:e005aa7145a3231658c7b50932c294d81b8f198ac2591f8f0c3e2429b035ad63
 size 22432460