End of training

README.md

@@ -1,7 +1,10 @@
 ---
-base_model: Edmon02/speecht5_finetuned_voxpopuli_hy
+license: mit
+base_model: Edmon02/speecht5_finetuned_hy
 tags:
 - generated_from_trainer
+datasets:
+- common_voice_17_0
 model-index:
 - name: speecht5_finetuned_voxpopuli_hy
   results: []
@@ -12,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_hy
 
-This model is a fine-tuned version of [Edmon02/speecht5_finetuned_voxpopuli_hy](https://huggingface.co/Edmon02/speecht5_finetuned_voxpopuli_hy) on the None dataset.
+This model is a fine-tuned version of [Edmon02/speecht5_finetuned_hy](https://huggingface.co/Edmon02/speecht5_finetuned_hy) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5734
+- Loss: 0.6810
 
 ## Model description
 
@@ -41,23 +44,27 @@ The following hyperparameters were used during training:
 - 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
+- lr_scheduler_warmup_steps: 250
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 0.6866        | 9.8401  | 1000 | 0.6304          |
-| 0.6736        | 19.6802 | 2000 | 0.6190          |
-| 0.6386        | 29.5203 | 3000 | 0.5798          |
-| 0.6381        | 39.3604 | 4000 | 0.5734          |
+| Training Loss | Epoch    | Step | Validation Loss |
+|:-------------:|:--------:|:----:|:---------------:|
+| 0.7562        | 12.5786  | 500  | 0.7180          |
+| 0.732         | 25.1572  | 1000 | 0.7013          |
+| 0.7185        | 37.7358  | 1500 | 0.6943          |
+| 0.7064        | 50.3145  | 2000 | 0.6893          |
+| 0.7138        | 62.8931  | 2500 | 0.6849          |
+| 0.6973        | 75.4717  | 3000 | 0.6825          |
+| 0.6933        | 88.0503  | 3500 | 0.6817          |
+| 0.6939        | 100.6289 | 4000 | 0.6810          |
 
 
 ### Framework versions
 
-- Transformers 4.43.3
-- Pytorch 2.4.0+cu121
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "max_length": 1876,
   "pad_token_id": 1,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.42.4"
 }