End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: microsoft/speecht5_tts
+base_model: pedropauletti/speecht5_finetuned_common_voice_pt
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_common_voice_pt
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
+This model is a fine-tuned version of [pedropauletti/speecht5_finetuned_common_voice_pt](https://huggingface.co/pedropauletti/speecht5_finetuned_common_voice_pt) on the common_voice_11_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4776
+- Loss: 0.4610
 
 ## Model description
 
@@ -37,23 +37,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
-- eval_batch_size: 1
+- train_batch_size: 4
+- eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 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: 3000
+- training_steps: 4000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5629        | 3.29  | 1000 | 0.5044          |
-| 0.5157        | 6.58  | 2000 | 0.4866          |
-| 0.5117        | 9.87  | 3000 | 0.4776          |
+| 0.4962        | 6.58  | 1000 | 0.4737          |
+| 0.4823        | 13.16 | 2000 | 0.4651          |
+| 0.4824        | 19.74 | 3000 | 0.4612          |
+| 0.4845        | 26.32 | 4000 | 0.4610          |
 
 
 ### Framework versions