End of training

README.md

@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 # SpeechT5 fine-tuning
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the PeekieTech data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4379
 
 ## Model description
 
@@ -46,11 +48,14 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.4587        | 14.2857 | 2000 | 0.4379          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf3fcd0cfece43b936b82f279836790059b76010d8ca8f6effbedb13e6aef30
+oid sha256:2a9a9f331ce8618aeaa376936b22951defe37af3a9c4588f612fd632658eae03
 size 577789320