End of training

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9064
-- Cer: 50.5772
+- Loss: 0.9011
+- Cer: 50.3995
 
 ## Model description
 
@@ -48,7 +48,7 @@ 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_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 3.6
 
 ### Training results
 
@@ -56,14 +56,18 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:-------:|:---------------:|
 | 1.1421        | 0.4   | 1000 | 61.1639 | 1.1692          |
 | 1.0556        | 0.8   | 2000 | 51.7749 | 1.0215          |
-| 0.7837        | 1.2   | 3000 | 0.9572  | 54.1978         |
-| 0.7332        | 1.6   | 4000 | 0.9230  | 50.3966         |
-| 0.6957        | 2.0   | 5000 | 0.9064  | 50.5772         |
+| 0.7837        | 1.2   | 3000 | 54.1978 | 0.9572          |
+| 0.7332        | 1.6   | 4000 | 50.3966 | 0.9230          |
+| 0.6957        | 2.0   | 5000 | 50.5772 | 0.9064          |
+| 0.6211        | 2.4   | 6000 | 0.9177  | 49.8590         |
+| 0.5584        | 2.8   | 7000 | 0.8962  | 47.5366         |
+| 0.3952        | 3.2   | 8000 | 0.9025  | 48.2925         |
+| 0.4248        | 3.6   | 9000 | 0.9011  | 50.3995         |
 
 
 ### Framework versions
 
-- Transformers 4.40.1
+- Transformers 4.40.2
 - Pytorch 2.1.2
 - Datasets 2.19.1
 - Tokenizers 0.19.1

generation_config.json

@@ -262,5 +262,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.40.2"
 }