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 pphuc25/EngMed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1212
-- Wer: 50.5798
+- Loss: 3.0716
+- Wer: 52.2789
 
 ## 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     |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|
-| 1.0819        | 1.0   | 2506  | 1.6886          | 51.9192 |
-| 0.594         | 2.0   | 5012  | 1.7069          | 51.3181 |
-| 0.2363        | 3.0   | 7518  | 1.8735          | 51.3086 |
-| 0.0576        | 4.0   | 10024 | 2.0377          | 50.6129 |
-| 0.0116        | 5.0   | 12530 | 2.1212          | 50.5798 |
+| 1.1558        | 1.0   | 2506  | 1.7618          | 61.5410 |
+| 0.7056        | 2.0   | 5012  | 1.8179          | 51.1240 |
+| 0.4179        | 3.0   | 7518  | 2.0105          | 51.7298 |
+| 0.2239        | 4.0   | 10024 | 2.2419          | 55.2747 |
+| 0.1215        | 5.0   | 12530 | 2.4194          | 52.5344 |
+| 0.1093        | 6.0   | 15036 | 2.5205          | 52.8089 |
+| 0.0801        | 7.0   | 17542 | 2.6161          | 55.1091 |
+| 0.0546        | 8.0   | 20048 | 2.6225          | 54.4370 |
+| 0.0434        | 9.0   | 22554 | 2.7782          | 53.2207 |
+| 0.0259        | 10.0  | 25060 | 2.8240          | 54.5459 |
+| 0.0261        | 11.0  | 27566 | 2.8877          | 53.2349 |
+| 0.0082        | 12.0  | 30072 | 2.9535          | 51.8056 |
+| 0.0086        | 13.0  | 32578 | 2.9738          | 53.7886 |
+| 0.0206        | 14.0  | 35084 | 2.9812          | 52.5818 |
+| 0.0036        | 15.0  | 37590 | 2.9906          | 53.1213 |
+| 0.0028        | 16.0  | 40096 | 2.9971          | 52.7616 |
+| 0.0048        | 17.0  | 42602 | 3.0191          | 52.6811 |
+| 0.0048        | 18.0  | 45108 | 3.0563          | 51.2660 |
+| 0.0029        | 19.0  | 47614 | 3.0625          | 51.9381 |
+| 0.001         | 20.0  | 50120 | 3.0716          | 52.2789 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6a447fbcc5e193083f9637ab52c28475d2f5f1feb67f7194367c91b674704b
+oid sha256:f6180515aba832567319cbf5c92e338d6c237525732bcd9494f7a5f6ab4547d5
 size 966995080