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-base](https://huggingface.co/openai/whisper-base) on the Common Voice 16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6072
-- Cer: 13.4234
+- Loss: 0.5929
+- Cer: 13.2243
 
 ## Model description
 
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 2.3485        | 1.01  | 100  | 0.9561          | 22.0674 |
-| 0.6035        | 2.02  | 200  | 0.7036          | 16.4046 |
-| 0.3438        | 3.03  | 300  | 0.6294          | 14.7272 |
-| 0.2082        | 4.04  | 400  | 0.6100          | 14.1940 |
-| 0.1266        | 5.05  | 500  | 0.6072          | 13.4234 |
+| Training Loss | Epoch  | Step | Validation Loss | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 2.3402        | 1.0101 | 100  | 0.9377          | 20.2765 |
+| 0.5917        | 2.0202 | 200  | 0.6871          | 16.3785 |
+| 0.3349        | 3.0303 | 300  | 0.6126          | 15.5452 |
+| 0.2024        | 4.0404 | 400  | 0.5887          | 14.1160 |
+| 0.1236        | 5.0505 | 500  | 0.5929          | 13.2243 |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

generation_config.json

@@ -252,5 +252,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.40.0"
 }