End of training

README.md

@@ -20,8 +20,8 @@ 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 Premier dataset organisé de 52 Hertz dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6515
-- Wer: 50.8197
+- Loss: 0.8247
+- Wer: 54.8550
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -56,21 +56,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer      |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.8143        | 1.0   | 12   | 1.7762          | 224.3380 |
-| 2.5616        | 2.0   | 24   | 1.4181          | 203.6570 |
-| 1.5828        | 3.0   | 36   | 1.0865          | 97.9823  |
-| 1.3432        | 4.0   | 48   | 0.9156          | 63.4300  |
-| 1.0252        | 5.0   | 60   | 0.8267          | 60.1513  |
-| 0.8575        | 6.0   | 72   | 0.7743          | 54.6028  |
-| 0.7936        | 7.0   | 84   | 0.7340          | 50.4414  |
-| 0.6994        | 8.0   | 96   | 0.7078          | 52.5851  |
-| 0.6296        | 9.0   | 108  | 0.6846          | 50.9458  |
-| 0.6202        | 10.0  | 120  | 0.6735          | 49.0542  |
-| 0.5209        | 11.0  | 132  | 0.6640          | 49.5586  |
-| 0.5774        | 12.0  | 144  | 0.6573          | 49.9369  |
-| 0.5396        | 13.0  | 156  | 0.6534          | 50.9458  |
-| 0.5082        | 14.0  | 168  | 0.6517          | 50.8197  |
-| 0.5131        | 15.0  | 180  | 0.6515          | 50.8197  |
+| 4.0401        | 1.0   | 12   | 1.9871          | 318.7894 |
+| 3.0292        | 2.0   | 24   | 1.5979          | 231.2736 |
+| 2.1219        | 3.0   | 36   | 1.3870          | 159.0164 |
+| 1.8719        | 4.0   | 48   | 1.2319          | 100.3783 |
+| 1.5391        | 5.0   | 60   | 1.0939          | 70.3657  |
+| 1.3396        | 6.0   | 72   | 0.9996          | 78.8146  |
+| 1.2744        | 7.0   | 84   | 0.9322          | 60.9079  |
+| 1.1095        | 8.0   | 96   | 0.8928          | 77.9319  |
+| 1.031         | 9.0   | 108  | 0.8677          | 57.6293  |
+| 1.063         | 10.0  | 120  | 0.8508          | 56.3682  |
+| 0.8875        | 11.0  | 132  | 0.8354          | 55.7377  |
+| 0.9782        | 12.0  | 144  | 0.8293          | 56.3682  |
+| 0.9283        | 13.0  | 156  | 0.8265          | 54.8550  |
+| 0.9001        | 14.0  | 168  | 0.8251          | 54.3506  |
+| 0.8938        | 15.0  | 180  | 0.8247          | 54.8550  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ecb2c3f66343982dfb57327959b75ef26788025b8fd7fa742056747f2dfb3a
+oid sha256:b5e2fad7f2ac23905ab9abd4b9f740deef1ffdfe7fa0e64d4284c6a4090f05b6
 size 151061672

runs/Jan15_22-29-05_sl-tp-br-518/events.out.tfevents.1768512553.sl-tp-br-518.400926.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79598bc6161af9abb81e230eea5cd8f9240896e242a212397aef0bf8dd515dc0
-size 16976
+oid sha256:1e6176eb20e94f841b94f37dfca2120835dd843481d9e80e59882452af34d297
+size 19339