update model card README.md

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2-large-xls-r-1b-wolof-VoiceToText
   results: []
@@ -12,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-large-xls-r-1b-wolof-VoiceToText
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+This model is a fine-tuned version of [BenDaouda/wav2vec2-large-xls-r-1b-wolof-VoiceToText](https://huggingface.co/BenDaouda/wav2vec2-large-xls-r-1b-wolof-VoiceToText) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4722
+- Wer: 0.4276
 
 ## Model description
 
@@ -32,18 +37,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 30
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.2628        | 14.29 | 400  | 0.5651          | 0.5578 |
+| 0.2354        | 28.57 | 800  | 0.4722          | 0.4276 |
 
 
 ### Framework versions