End of training

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 48.484848484848484
+      value: 57.57575757575758
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ 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 Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9481
-- Wer: 48.4848
+- Loss: 1.1971
+- Wer: 57.5758
 
 ## Model description
 
@@ -56,39 +56,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 10
-- training_steps: 1000
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.4571        | 6.25   | 50   | 0.8148          | 51.5152 |
-| 0.0064        | 12.5   | 100  | 0.8425          | 48.4848 |
-| 0.001         | 18.75  | 150  | 0.8638          | 50.9091 |
-| 0.0006        | 25.0   | 200  | 0.8758          | 52.1212 |
-| 0.0004        | 31.25  | 250  | 0.8870          | 52.1212 |
-| 0.0003        | 37.5   | 300  | 0.8961          | 49.6970 |
-| 0.0003        | 43.75  | 350  | 0.9042          | 49.6970 |
-| 0.0002        | 50.0   | 400  | 0.9111          | 48.4848 |
-| 0.0002        | 56.25  | 450  | 0.9159          | 48.4848 |
-| 0.0002        | 62.5   | 500  | 0.9229          | 48.4848 |
-| 0.0002        | 68.75  | 550  | 0.9276          | 48.4848 |
-| 0.0001        | 75.0   | 600  | 0.9319          | 48.4848 |
-| 0.0001        | 81.25  | 650  | 0.9355          | 48.4848 |
-| 0.0001        | 87.5   | 700  | 0.9388          | 48.4848 |
-| 0.0001        | 93.75  | 750  | 0.9412          | 48.4848 |
-| 0.0001        | 100.0  | 800  | 0.9439          | 48.4848 |
-| 0.0001        | 106.25 | 850  | 0.9453          | 48.4848 |
-| 0.0001        | 112.5  | 900  | 0.9469          | 48.4848 |
-| 0.0001        | 118.75 | 950  | 0.9473          | 48.4848 |
-| 0.0001        | 125.0  | 1000 | 0.9481          | 48.4848 |
+| 0.0001        | 250.0  | 1000 | 1.0531          | 53.9394 |
+| 0.0           | 500.0  | 2000 | 1.1288          | 56.3636 |
+| 0.0           | 750.0  | 3000 | 1.1782          | 58.1818 |
+| 0.0           | 1000.0 | 4000 | 1.1971          | 57.5758 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5136466c2b81cd10d52b80b1dd3f6bf28b724f54950ec2a80897b12ff9848c
+oid sha256:ddcfdbd5edfaa83633b98207153d1e64dc94be44f19cf3ccf269f01a05c8e100
 size 966995080