update model card README.md

README.md

@@ -14,17 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2_xlsr
 
-## Training was stopped but going to be retrained
-
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset on spanish subset.
+This model is a fine-tuned version of [diallomama/wav2vec2_xlsr](https://huggingface.co/diallomama/wav2vec2_xlsr) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2546
-- eval_wer: 0.9870
-- eval_runtime: 918.8309
-- eval_samples_per_second: 16.422
-- eval_steps_per_second: 2.054
-- epoch: 0.63
-- step: 3200
+- eval_loss: 0.2204
+- eval_wer: 0.9719
+- eval_runtime: 923.0808
+- eval_samples_per_second: 16.346
+- eval_steps_per_second: 2.044
+- epoch: 1.66
+- step: 8400
 
 ## Model description
 
@@ -52,7 +50,7 @@ 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: 500
-- num_epochs: 15
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Framework versions