End of training

README.md

@@ -3,7 +3,7 @@ library_name: transformers
 language:
 - th
 license: apache-2.0
-base_model: biodatlab/whisper-th-small-combined
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.5863268446049903
+      value: 0.49260820121747273
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,10 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small Th Combined Finetuned
 
-This model is a fine-tuned version of [biodatlab/whisper-th-small-combined](https://huggingface.co/biodatlab/whisper-th-small-combined) on the Common Voice 17.0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1196
-- Wer: 0.5863
+- Loss: 0.0942
+- Wer: 0.4926
 
 ## Model description
 
@@ -74,10 +74,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.2959        | 0.9749 | 1000 | 0.1337          | 0.6218 |
-| 0.2512        | 1.9498 | 2000 | 0.1246          | 0.5924 |
-| 0.1948        | 2.9247 | 3000 | 0.1224          | 0.6163 |
-| 0.1812        | 3.8996 | 4000 | 0.1196          | 0.5863 |
+| 0.2215        | 0.2175 | 1000 | 0.1887          | 0.6911 |
+| 0.1717        | 0.4349 | 2000 | 0.1333          | 0.5892 |
+| 0.1397        | 0.6524 | 3000 | 0.1067          | 0.5247 |
+| 0.1275        | 0.8698 | 4000 | 0.0942          | 0.4926 |
 
 
 ### Framework versions

generation_config.json

@@ -250,8 +250,6 @@
     49870,
     50254,
     50258,
-    50358,
-    50359,
     50360,
     50361,
     50362