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-tiny](https://huggingface.co/openai/whisper-tiny) on the pphuc25/EngMed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1885
-- Wer: 64.3381
+- Loss: 3.4853
+- Wer: 66.7045
 
 ## Model description
 
@@ -46,17 +46,32 @@ 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_steps: 100
-- num_epochs: 5
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Wer     |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|
-| 1.2506        | 1.0   | 2506  | 1.8234          | 68.3468 |
-| 0.8111        | 2.0   | 5012  | 1.8613          | 63.4767 |
-| 0.4577        | 3.0   | 7518  | 1.9671          | 71.6598 |
-| 0.2581        | 4.0   | 10024 | 2.1055          | 63.3726 |
-| 0.1261        | 5.0   | 12530 | 2.1885          | 64.3381 |
+| 1.2768        | 1.0   | 2506  | 1.8614          | 66.7187 |
+| 0.9077        | 2.0   | 5012  | 1.9243          | 66.6383 |
+| 0.6044        | 3.0   | 7518  | 2.0816          | 71.3474 |
+| 0.4112        | 4.0   | 10024 | 2.2672          | 69.5064 |
+| 0.2788        | 5.0   | 12530 | 2.4746          | 65.6728 |
+| 0.1736        | 6.0   | 15036 | 2.6423          | 68.1196 |
+| 0.096         | 7.0   | 17542 | 2.7603          | 66.7897 |
+| 0.0632        | 8.0   | 20048 | 2.9008          | 68.4746 |
+| 0.046         | 9.0   | 22554 | 3.0145          | 69.8850 |
+| 0.0338        | 10.0  | 25060 | 3.0977          | 66.8749 |
+| 0.0203        | 11.0  | 27566 | 3.1614          | 67.5186 |
+| 0.0207        | 12.0  | 30072 | 3.2117          | 65.2847 |
+| 0.011         | 13.0  | 32578 | 3.3028          | 66.4253 |
+| 0.007         | 14.0  | 35084 | 3.3854          | 68.1102 |
+| 0.0071        | 15.0  | 37590 | 3.3962          | 66.8702 |
+| 0.0041        | 16.0  | 40096 | 3.4312          | 66.8323 |
+| 0.0043        | 17.0  | 42602 | 3.4244          | 66.5294 |
+| 0.0036        | 18.0  | 45108 | 3.4340          | 66.8512 |
+| 0.0019        | 19.0  | 47614 | 3.4810          | 67.6558 |
+| 0.0003        | 20.0  | 50120 | 3.4853          | 66.7045 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f82d110117f43bf0ee94dffb136f27ce3eaddac289d851a7bde3feed2c58bf
+oid sha256:cf03952d7d0fa23abb635f464cf409e1f4247e87b4dce8cd69674657ceaec7c8
 size 151061672