End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.2900923044740214
+      value: 0.3035849697983945
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2191
-- Wer: 0.2901
+- Loss: 0.2174
+- Wer: 0.3036
 
 ## Model description
 
@@ -67,11 +67,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.641         | 0.85  | 400  | 0.6924          | 0.8315 |
-| 0.3883        | 1.7   | 800  | 0.3241          | 0.4587 |
-| 0.2141        | 2.56  | 1200 | 0.2677          | 0.3845 |
-| 0.1489        | 3.41  | 1600 | 0.2448          | 0.3230 |
-| 0.1056        | 4.26  | 2000 | 0.2191          | 0.2901 |
+| 4.2112        | 0.85  | 400  | 2.6594          | 1.0    |
+| 0.6492        | 1.7   | 800  | 0.3441          | 0.4777 |
+| 0.2474        | 2.56  | 1200 | 0.2863          | 0.4044 |
+| 0.1756        | 3.41  | 1600 | 0.2588          | 0.3454 |
+| 0.1267        | 4.26  | 2000 | 0.2174          | 0.3036 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9837642d1ed299ce659b24ed455cd87d5e1e08d4c64c94453daaef454de7599
+oid sha256:d9dc9681ec2acb91950917a7960cd5545ec33e8458249a17d8688e29f8f95328
 size 1262037165