update model card README.md

README.md

@@ -15,9 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-xlsr-hausa2-demo-colab
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6617
-- Wer: 0.5962
 
 ## Model description
 
@@ -36,27 +33,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9.6e-05
+- learning_rate: 9.789e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 13
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 50
+- num_epochs: 40
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 6.9776        | 10.0  | 400  | 2.7735          | 1.0    |
-| 2.2732        | 20.0  | 800  | 0.7769          | 0.8212 |
-| 0.4471        | 30.0  | 1200 | 0.6199          | 0.6210 |
-| 0.2681        | 40.0  | 1600 | 0.6512          | 0.6022 |
-| 0.2191        | 50.0  | 2000 | 0.6617          | 0.5962 |
 
 
 ### Framework versions