End of training

README.md

@@ -20,7 +20,7 @@ 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 Custom Speech Dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6429
+- Loss: 0.6068
 
 ## Model description
 
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.1376        | 500.0  | 500  | 0.6191          |
-| 0.1163        | 1000.0 | 1000 | 0.6286          |
-| 0.1053        | 1500.0 | 1500 | 0.6523          |
-| 0.0996        | 2000.0 | 2000 | 0.6429          |
+| 0.1707        | 500.0  | 500  | 0.5661          |
+| 0.1255        | 1000.0 | 1000 | 0.5885          |
+| 0.1126        | 1500.0 | 1500 | 0.6017          |
+| 0.1066        | 2000.0 | 2000 | 0.6068          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8063499cd096e0e2e6d29c9cc204278d686154a078624161b56e391c923b71
+oid sha256:b02a0654d9bbc6ef40da9eae2e259e8f3c9530ac527719c81344dac15a0398fc
 size 577789320