End of training

README.md

@@ -7,18 +7,18 @@ tags:
 datasets:
 - facebook/voxpopuli
 model-index:
-- name: speecht5_finetuned_voxpopuli_fr
+- name: speecht5_finetuned_voxpopuli_it
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# speecht5_finetuned_voxpopuli_fr
+# speecht5_finetuned_voxpopuli_it
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4881
+- Loss: 0.4841
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 7e-06
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
@@ -46,16 +46,19 @@ 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: 7000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5485        | 6.13  | 1000 | 0.5096          |
-| 0.5225        | 12.26 | 2000 | 0.4941          |
-| 0.5149        | 18.39 | 3000 | 0.4907          |
-| 0.5189        | 24.52 | 4000 | 0.4881          |
+| 0.5625        | 4.72  | 1000 | 0.5168          |
+| 0.5329        | 9.43  | 2000 | 0.5001          |
+| 0.526         | 14.15 | 3000 | 0.4915          |
+| 0.5261        | 18.87 | 4000 | 0.4878          |
+| 0.5194        | 23.58 | 5000 | 0.4865          |
+| 0.5138        | 28.3  | 6000 | 0.4853          |
+| 0.5099        | 33.02 | 7000 | 0.4841          |
 
 
 ### Framework versions