End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3240
+- Loss: 1.2102
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.2569        | 500.0  | 500  | 1.2742          |
-| 0.1183        | 1000.0 | 1000 | 1.2840          |
-| 0.1014        | 1500.0 | 1500 | 1.2801          |
-| 0.1065        | 2000.0 | 2000 | 1.3240          |
+| 0.1494        | 500.0  | 500  | 0.9763          |
+| 0.0917        | 1000.0 | 1000 | 1.1197          |
+| 0.0901        | 1500.0 | 1500 | 1.2297          |
+| 0.095         | 2000.0 | 2000 | 1.2102          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad81036af431bb0050273860299742b2cf6277c3faea0b15f8eab08b72644874
+oid sha256:6a541b6f7d8bee6195f8a1f1833e41780584002e0e4837e5056c063e3e32ddca
 size 577789320

runs/Jul07_14-46-51_hem-MS-7D88/events.out.tfevents.1751878912.hem-MS-7D88.1560443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1348c4f4a6c1d0c6896d11a0f413093ec97e4a9b2c74bf06b1bf9c3760e16a
+size 24885

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c5d00a9cd75dd42989d09161fa837fb6840a02c73e212c34d234dc3221973f
+oid sha256:e3da22e46b94908d66258b463360bfba0a37bb4ec506d0e15cf5cd26580a9d47
 size 5905