End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.6470418470418471
+      value: 0.6463684463684464
 ---
 
 <!-- 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_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8808
-- Wer: 0.6470
+- Loss: 0.9138
+- Wer: 0.6464
 
 ## Model description
 
@@ -67,10 +67,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.8175        | 1.01  | 300  | 2.6262          | 0.9953 |
-| 1.504         | 2.02  | 600  | 1.1824          | 0.8302 |
-| 0.8864        | 3.03  | 900  | 0.9646          | 0.7269 |
-| 0.6101        | 4.03  | 1200 | 0.8808          | 0.6470 |
+| 5.6958        | 1.01  | 300  | 2.5593          | 0.9952 |
+| 1.4881        | 2.02  | 600  | 1.2057          | 0.8310 |
+| 0.8911        | 3.03  | 900  | 0.9897          | 0.7268 |
+| 0.6118        | 4.03  | 1200 | 0.9138          | 0.6464 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e3163e67bc8a9852f73d0375187b326beb2482e02223b95b50b71b61db26b
+oid sha256:76519c3af165b7497b0c3e12654549fa0fd87259529667dcd7d9309a1a3d93e9
 size 1262078125