End of training

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: openai/whisper-base
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: whisper-base-akan
   results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-base-akan
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0030
+- Wer: 41.5869
 
 ## Model description
 
@@ -43,6 +48,20 @@ The following hyperparameters were used during training:
 - training_steps: 2000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.2883        | 5.0   | 250  | 0.7379          | 70.2488 |
+| 0.0873        | 10.0  | 500  | 0.8617          | 49.6246 |
+| 0.0373        | 15.0  | 750  | 0.9027          | 47.4165 |
+| 0.0204        | 20.0  | 1000 | 0.9374          | 44.5017 |
+| 0.0078        | 25.0  | 1250 | 0.9861          | 44.0601 |
+| 0.0014        | 30.0  | 1500 | 0.9873          | 42.1758 |
+| 0.0003        | 35.0  | 1750 | 0.9982          | 41.4544 |
+| 0.0003        | 40.0  | 2000 | 1.0030          | 41.5869 |
+
+
 ### Framework versions
 
 - Transformers 4.45.2

generation_config.json

@@ -39,7 +39,6 @@
   ],
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
-  "dropout": 0.01,
   "eos_token_id": 50257,
   "is_multilingual": true,
   "lang_to_id": {