update model card README.md

README.md

@@ -1,10 +1,6 @@
 ---
-language:
-- ar
 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 - AR 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: 1.3742
-- Wer: 0.9387
+- Loss: 1.4191
+- Wer: 0.9357
 
 ## Model description
 
@@ -41,44 +37,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 6.5e-05
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 20.0
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 10.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Wer    |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 2.6638        | 0.84  | 500   | 2.3852          | 0.9974 |
-| 2.6578        | 1.67  | 1000  | 2.2796          | 0.9971 |
-| 2.6016        | 2.51  | 1500  | 2.0046          | 0.9961 |
-| 2.5752        | 3.35  | 2000  | 1.9606          | 0.9961 |
-| 2.539         | 4.19  | 2500  | 1.8836          | 0.9940 |
-| 2.5214        | 5.03  | 3000  | 1.8593          | 0.9933 |
-| 2.4684        | 5.86  | 3500  | 1.7816          | 0.9885 |
-| 2.4134        | 6.7   | 4000  | 1.7168          | 0.9808 |
-| 2.3732        | 7.54  | 4500  | 1.6406          | 0.9764 |
-| 2.3371        | 8.37  | 5000  | 1.6087          | 0.9739 |
-| 2.2824        | 9.21  | 5500  | 1.5476          | 0.9696 |
-| 2.3771        | 10.05 | 6000  | 1.6468          | 0.9773 |
-| 2.3499        | 10.89 | 6500  | 1.6116          | 0.9737 |
-| 2.3283        | 11.72 | 7000  | 1.6059          | 0.9744 |
-| 2.3153        | 12.56 | 7500  | 1.5889          | 0.9758 |
-| 2.3016        | 13.4  | 8000  | 1.5663          | 0.9728 |
-| 2.2731        | 14.24 | 8500  | 1.5674          | 0.9626 |
-| 2.2617        | 15.08 | 9000  | 1.5032          | 0.9583 |
-| 2.2252        | 15.91 | 9500  | 1.4662          | 0.9516 |
-| 2.2048        | 16.75 | 10000 | 1.4411          | 0.9561 |
-| 2.1731        | 17.59 | 10500 | 1.4228          | 0.9521 |
-| 2.1732        | 18.43 | 11000 | 1.4053          | 0.9429 |
-| 2.1502        | 19.26 | 11500 | 1.3828          | 0.9400 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 2.2416        | 0.84  | 500  | 1.2867          | 0.8875 |
+| 2.3089        | 1.67  | 1000 | 1.8336          | 0.9548 |
+| 2.3614        | 2.51  | 1500 | 1.5937          | 0.9469 |
+| 2.5234        | 3.35  | 2000 | 1.9765          | 0.9867 |
+| 2.5373        | 4.19  | 2500 | 1.9062          | 0.9916 |
+| 2.5703        | 5.03  | 3000 | 1.9772          | 0.9915 |
+| 2.4656        | 5.86  | 3500 | 1.8083          | 0.9829 |
+| 2.4339        | 6.7   | 4000 | 1.7548          | 0.9752 |
+| 2.344         | 7.54  | 4500 | 1.6146          | 0.9638 |
+| 2.2677        | 8.38  | 5000 | 1.5105          | 0.9499 |
+| 2.2074        | 9.21  | 5500 | 1.4191          | 0.9357 |
 
 
 ### Framework versions