update model card README.md

README.md

@@ -1,8 +1,5 @@
 ---
-license: apache-2.0
 tags:
-- automatic-speech-recognition
-- abdusahmbzuai/arabic_speech_massive_300hrs
 - generated_from_trainer
 model-index:
 - name: aradia-ctc-hubert-ft
@@ -14,10 +11,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # aradia-ctc-hubert-ft
 
-This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the ABDUSAHMBZUAI/ARABIC_SPEECH_MASSIVE_300HRS - NA dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6946
-- Wer: 0.3940
+- Loss: 0.8536
+- Wer: 0.3737
 
 ## Model description
 
@@ -45,7 +42,7 @@ 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: 15.0
+- num_epochs: 30.0
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -84,8 +81,43 @@ The following hyperparameters were used during training:
 | 0.3919        | 13.04 | 3000 | 0.6778          | 0.3966 |
 | 0.3919        | 13.48 | 3100 | 0.6872          | 0.3971 |
 | 0.3919        | 13.91 | 3200 | 0.6882          | 0.3945 |
-| 0.3919        | 14.35 | 3300 | 0.6938          | 0.3937 |
-| 0.3919        | 14.78 | 3400 | 0.6928          | 0.3946 |
+| 0.3919        | 14.35 | 3300 | 0.7177          | 0.4010 |
+| 0.3919        | 14.78 | 3400 | 0.6888          | 0.4043 |
+| 0.3767        | 15.22 | 3500 | 0.7124          | 0.4202 |
+| 0.3767        | 15.65 | 3600 | 0.7276          | 0.4120 |
+| 0.3767        | 16.09 | 3700 | 0.7265          | 0.4034 |
+| 0.3767        | 16.52 | 3800 | 0.7392          | 0.4077 |
+| 0.3767        | 16.95 | 3900 | 0.7403          | 0.3965 |
+| 0.3603        | 17.39 | 4000 | 0.7445          | 0.4016 |
+| 0.3603        | 17.82 | 4100 | 0.7579          | 0.4012 |
+| 0.3603        | 18.26 | 4200 | 0.7225          | 0.3963 |
+| 0.3603        | 18.69 | 4300 | 0.7355          | 0.3951 |
+| 0.3603        | 19.13 | 4400 | 0.7482          | 0.3925 |
+| 0.3153        | 19.56 | 4500 | 0.7723          | 0.3972 |
+| 0.3153        | 20.0  | 4600 | 0.7469          | 0.3898 |
+| 0.3153        | 20.43 | 4700 | 0.7800          | 0.3944 |
+| 0.3153        | 20.87 | 4800 | 0.7827          | 0.3897 |
+| 0.3153        | 21.3  | 4900 | 0.7935          | 0.3914 |
+| 0.286         | 21.74 | 5000 | 0.7984          | 0.3750 |
+| 0.286         | 22.17 | 5100 | 0.7945          | 0.3830 |
+| 0.286         | 22.61 | 5200 | 0.8011          | 0.3775 |
+| 0.286         | 23.04 | 5300 | 0.7978          | 0.3824 |
+| 0.286         | 23.48 | 5400 | 0.8161          | 0.3833 |
+| 0.2615        | 23.91 | 5500 | 0.7823          | 0.3858 |
+| 0.2615        | 24.35 | 5600 | 0.8312          | 0.3863 |
+| 0.2615        | 24.78 | 5700 | 0.8427          | 0.3819 |
+| 0.2615        | 25.22 | 5800 | 0.8432          | 0.3802 |
+| 0.2615        | 25.65 | 5900 | 0.8286          | 0.3794 |
+| 0.2408        | 26.09 | 6000 | 0.8224          | 0.3824 |
+| 0.2408        | 26.52 | 6100 | 0.8228          | 0.3823 |
+| 0.2408        | 26.95 | 6200 | 0.8324          | 0.3795 |
+| 0.2408        | 27.39 | 6300 | 0.8564          | 0.3744 |
+| 0.2408        | 27.82 | 6400 | 0.8629          | 0.3774 |
+| 0.2254        | 28.26 | 6500 | 0.8545          | 0.3778 |
+| 0.2254        | 28.69 | 6600 | 0.8492          | 0.3767 |
+| 0.2254        | 29.13 | 6700 | 0.8511          | 0.3751 |
+| 0.2254        | 29.56 | 6800 | 0.8491          | 0.3753 |
+| 0.2254        | 30.0  | 6900 | 0.8536          | 0.3737 |
 
 
 ### Framework versions