End of training

README.md

@@ -17,7 +17,7 @@ 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 voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4592
+- Loss: 0.5278
 
 ## Model description
 
@@ -45,16 +45,14 @@ 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: 2000
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5216        | 4.3   | 1000 | 0.4788          |
-| 0.4935        | 8.61  | 2000 | 0.4652          |
-| 0.4928        | 12.91 | 3000 | 0.4629          |
-| 0.4949        | 17.21 | 4000 | 0.4592          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4988        | 94.12  | 1000 | 0.5202          |
+| 0.4767        | 188.24 | 2000 | 0.5278          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d13809924b62265e128b41f833bb537048f74716ff11dcd7444b512722921a9
+oid sha256:ad5f54abf39a92633835aab3593bb40d517a4b0382b2b246718d38caeb137d8b
 size 577878333