update model card README.md

README.md

@@ -4,9 +4,24 @@ tags:
 - generated_from_trainer
 datasets:
 - fleurs
+metrics:
+- wer
 model-index:
 - name: openai/whisper-tiny
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: fleurs
+      type: fleurs
+      config: sv_se
+      split: validation
+      args: sv_se
+    metrics:
+    - name: Wer
+      type: wer
+      value: 153.2258064516129
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,6 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 # openai/whisper-tiny
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6192
+- Wer: 153.2258
 
 ## Model description
 
@@ -43,6 +61,14 @@ The following hyperparameters were used during training:
 - training_steps: 2
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer      |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.565         | 0.5   | 1    | 1.6192          | 153.2258 |
+| 1.3028        | 1.0   | 2    | 1.6192          | 153.2258 |
+
+
 ### Framework versions
 
 - Transformers 4.26.0.dev0