update model card README.md

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: facebook/wav2vec2-base
+base_model: classla/wav2vec2-xls-r-parlaspeech-hr
 tags:
 - generated_from_trainer
 datasets:
@@ -30,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xlsr-finetuned
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
+This model is a fine-tuned version of [classla/wav2vec2-xls-r-parlaspeech-hr](https://huggingface.co/classla/wav2vec2-xls-r-parlaspeech-hr) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 2.1218
 - Wer: 1.0
 
 ## Model description
@@ -61,20 +60,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
-- training_steps: 8
+- training_steps: 4
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| No log        | 1.0   | 1    | 18.8467         | 1.0 |
-| 4.2137        | 2.0   | 2    | 18.8546         | 1.0 |
-| 4.2137        | 3.0   | 3    | 18.8671         | 1.0 |
-| 4.2108        | 4.0   | 4    | nan             | 1.0 |
-| 4.2108        | 5.0   | 5    | nan             | 1.0 |
-| 0.0           | 6.0   | 6    | nan             | 1.0 |
-| 0.0           | 7.0   | 7    | nan             | 1.0 |
-| 0.0           | 8.0   | 8    | nan             | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer  |
+|:-------------:|:-----:|:----:|:---------------:|:----:|
+| No log        | 1.0   | 1    | 14.0503         | 20.0 |
+| 3.5057        | 2.0   | 2    | 5.3734          | 4.0  |
+| 3.5057        | 3.0   | 3    | 2.8914          | 1.0  |
+| 1.0014        | 4.0   | 4    | 2.1218          | 1.0  |
 
 
 ### Framework versions