update model card README.md

README.md

@@ -21,33 +21,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.15077102723494865
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: common_voice_13_0
-      type: common_voice_13_0
-      config: fy-NL
-      split: test
-      args: fy-NL
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.13990069099621516
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: common_voice_8_0
-      type: common_voice_8_0
-      config: fy-NL
-      split: test
-      args: fy-NL
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.14409596762537938
+      value: 0.1492598825428444
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -57,31 +31,23 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2206
-- Wer: 0.1508
-
-And for the test set:
-- Wer: 0.1399
+- Loss: 0.2204
+- Wer: 0.1493
 
-When evaluated on common_voice_8_0 dataset:
-- Wer: 0.1441
+## Model description
 
-This model was developed together with [golesheed](https://huggingface.co/golesheed) for the course "Speech Recognition II" of the "MSc Voice Technology" program at Rijksuniversiteit Groningen - Campus Fryslân.
+More information needed
 
 ## Intended uses & limitations
 
-Intended use is for recognizing Frisian speech.
-
-Main limitation is no LM rescoring.
+More information needed
 
 ## Training and evaluation data
 
-Training and evaluation splits used are the ones available in the Common Voice dataset.
+More information needed
 
 ## Training procedure
 
-To be added later once the notebook used for training is pushed to GitHub.
-
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -94,7 +60,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 60
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -120,11 +86,6 @@ The following hyperparameters were used during training:
 | 0.5204        | 41.76 | 5100 | 0.2181          | 0.1587 |
 | 0.512         | 44.21 | 5400 | 0.2263          | 0.1607 |
 | 0.465         | 46.66 | 5700 | 0.2204          | 0.1493 |
-| 0.4482        | 49.11 | 6000 | 0.2143          | 0.1527 |
-| 0.3972        | 51.63 | 6300 | 0.2198          | 0.1617 |
-| 0.3168        | 54.09 | 6600 | 0.2170          | 0.1528 |
-| 0.2432        | 56.53 | 6900 | 0.2182          | 0.1529 |
-| 0.252         | 58.98 | 7200 | 0.2206          | 0.1508 |
 
 
 ### Framework versions