update model card README.md

README.md

@@ -1,10 +1,6 @@
 ---
-language:
-- de
 license: apache-2.0
 tags:
-- automatic-speech-recognition
-- mozilla-foundation/common_voice_8_0
 - generated_from_trainer
 datasets:
 - common_voice
@@ -18,10 +14,10 @@ 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 MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - DE dataset.
+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 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1355
-- Wer: 0.1532
+- Wer: 0.1531
 
 ## Model description
 
@@ -41,15 +37,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 7.5e-05
-- train_batch_size: 8
+- train_batch_size: 64
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- 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: 2000
-- num_epochs: 2.5
+- num_epochs: 3.0
 - mixed_precision_training: Native AMP
 
 ### Training results