End of training

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # speecht5_finetuned_voxpopuli_sl
 
 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: 0.5157
 
 ## Model description
 
@@ -35,16 +37,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
+- train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 8
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 32
 - 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 results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5152        | 91.95  | 500  | 0.5177          |
+| 0.4734        | 183.91 | 1000 | 0.5199          |
+| 0.4555        | 275.86 | 1500 | 0.5129          |
+| 0.4464        | 367.82 | 2000 | 0.5133          |
+| 0.437         | 459.77 | 2500 | 0.5097          |
+| 0.4342        | 551.72 | 3000 | 0.5152          |
+| 0.426         | 643.68 | 3500 | 0.5153          |
+| 0.426         | 735.63 | 4000 | 0.5157          |
+
+
 ### Framework versions
 
 - Transformers 4.33.0.dev0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3838bac7683776f66bbf38154deb62780dc195b28e9bf6b0c10f53ae1d3d315
+oid sha256:bff31761d55847856dbabf5136ecddb6cd9e3245ac7a9cb05d8f14bf1c9a719f
 size 577878333