End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.578397212543554
+      value: 0.7456445993031359
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0807
-- Wer: 0.5784
-- Cer: 0.2011
+- Loss: 1.1185
+- Wer: 0.7456
+- Cer: 0.2727
 
 ## Model description
 
@@ -54,7 +54,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -70,22 +70,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 8.936         | 6.25  | 100  | 3.9640          | 1.0    | 1.0    |
-| 3.1468        | 12.5  | 200  | 2.9364          | 1.0    | 1.0    |
-| 2.9593        | 18.75 | 300  | 2.8629          | 1.0    | 1.0    |
-| 2.8306        | 25.0  | 400  | 2.6370          | 1.0    | 0.9985 |
-| 2.2935        | 31.25 | 500  | 1.8202          | 0.9512 | 0.5583 |
-| 1.5483        | 37.5  | 600  | 1.2877          | 0.8641 | 0.3397 |
-| 1.1782        | 43.75 | 700  | 1.0885          | 0.6864 | 0.2468 |
-| 0.968         | 50.0  | 800  | 1.0547          | 0.6341 | 0.2376 |
-| 0.7807        | 56.25 | 900  | 1.1017          | 0.6098 | 0.2308 |
-| 0.6741        | 62.5  | 1000 | 1.0517          | 0.5854 | 0.2125 |
-| 0.5715        | 68.75 | 1100 | 1.0351          | 0.5575 | 0.1988 |
-| 0.5277        | 75.0  | 1200 | 1.0396          | 0.5470 | 0.2018 |
-| 0.4874        | 81.25 | 1300 | 1.0805          | 0.5749 | 0.2094 |
-| 0.4649        | 87.5  | 1400 | 1.0880          | 0.5714 | 0.2072 |
-| 0.4497        | 93.75 | 1500 | 1.0827          | 0.5819 | 0.2026 |
-| 0.4164        | 100.0 | 1600 | 1.0807          | 0.5784 | 0.2011 |
+| 11.2364       | 6.25  | 100  | 7.3069          | 1.0    | 1.0    |
+| 3.7286        | 12.5  | 200  | 3.0929          | 1.0    | 1.0    |
+| 3.0568        | 18.75 | 300  | 2.9665          | 1.0    | 1.0    |
+| 2.9537        | 25.0  | 400  | 2.8605          | 1.0    | 1.0    |
+| 2.9037        | 31.25 | 500  | 2.8159          | 1.0    | 1.0    |
+| 2.788         | 37.5  | 600  | 2.6215          | 1.0    | 0.9954 |
+| 2.5724        | 43.75 | 700  | 2.2760          | 1.0    | 0.8979 |
+| 2.2313        | 50.0  | 800  | 1.8469          | 0.9686 | 0.5674 |
+| 1.9029        | 56.25 | 900  | 1.5598          | 0.9477 | 0.4478 |
+| 1.6884        | 62.5  | 1000 | 1.4081          | 0.9617 | 0.3991 |
+| 1.5275        | 68.75 | 1100 | 1.2847          | 0.9024 | 0.3511 |
+| 1.4569        | 75.0  | 1200 | 1.2333          | 0.8711 | 0.3359 |
+| 1.3648        | 81.25 | 1300 | 1.1766          | 0.8293 | 0.3115 |
+| 1.3107        | 87.5  | 1400 | 1.1461          | 0.7840 | 0.2833 |
+| 1.3094        | 93.75 | 1500 | 1.1227          | 0.7631 | 0.2772 |
+| 1.2793        | 100.0 | 1600 | 1.1185          | 0.7456 | 0.2727 |
 
 
 ### Framework versions