update model card README.md

README.md

@@ -1,6 +1,7 @@
 ---
 language:
-- ab
+- sv-SE
+license: apache-2.0
 tags:
 - automatic-speech-recognition
 - mozilla-foundation/common_voice_7_0
@@ -17,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 
 
-This model is a fine-tuned version of [hf-test/xls-r-dummy](https://huggingface.co/hf-test/xls-r-dummy) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 156.8789
-- Wer: 1.3456
+- Loss: 1.5563
+- Wer: 0.9487
 
 ## Model description
 
@@ -39,17 +40,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 2
+- learning_rate: 7.5e-05
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 10
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 5.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 2.9069        | 1.45  | 500  | 2.9047          | 1.0    |
+| 2.5875        | 2.91  | 1000 | 2.4159          | 1.1997 |
+| 2.2043        | 4.36  | 1500 | 1.6192          | 0.9598 |
 
 
 ### Framework versions