End of training

README.md

@@ -19,7 +19,7 @@ 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 Mozilla Common Voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5510
+- Loss: 0.5300
 
 ## Model description
 
@@ -47,17 +47,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 8000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 0.6481        | 6.8966  | 1000 | 0.5993          |
-| 0.6088        | 13.7931 | 2000 | 0.5672          |
-| 0.5753        | 20.6897 | 3000 | 0.5513          |
-| 0.5827        | 27.5862 | 4000 | 0.5510          |
+| 0.55          | 13.7931 | 2000 | 0.5357          |
+| 0.5315        | 27.5862 | 4000 | 0.5289          |
+| 0.5388        | 41.3793 | 6000 | 0.5332          |
+| 0.5345        | 55.1724 | 8000 | 0.5300          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f80a72734733b42dce4ae06778ced82ba3e9fe8e6655e14cc79d62ac9f1b295
+oid sha256:056c1cecc8142e78ba846c426d37db62871e573b1071fd661cd409817d64b540
 size 577789320