update model card README.md

README.md

@@ -1,56 +1,11 @@
 ---
-language: 
-- ur
-license: apache-2.0
 tags:
-- automatic-speech-recognition
-- robust-speech-event
+- generated_from_trainer
 datasets:
 - common_voice
-metrics:
-- wer
-- cer
 model-index:
 - name: wav2vec2-large-xlsr-53-urdu
-  results:
-  - task: 
-      type: automatic-speech-recognition  # Required. Example: automatic-speech-recognition
-      name: Urdu Speech Recognition  # Optional. Example: Speech Recognition
-    dataset:
-      type: common_voice  # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
-      name: Urdu  # Required. Example: Common Voice zh-CN
-      args: ur         # Optional. Example: zh-CN
-    metrics:
-      - type: wer    # Required. Example: wer
-        value: 57.7  # Required. Example: 20.90
-        name: Test WER    # Optional. Example: Test WER
-        args: 
-        - learning_rate: 0.0003
-        - train_batch_size: 16
-        - eval_batch_size: 8
-        - seed: 42
-        - 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: 200
-        - num_epochs: 50
-        - mixed_precision_training: Native AMP         # Optional. Example for BLEU: max_order
-      - type: cer    # Required. Example: wer
-        value: 33.8  # Required. Example: 20.90
-        name: Test CER    # Optional. Example: Test WER
-        args: 
-        - learning_rate: 0.0003
-        - train_batch_size: 16
-        - eval_batch_size: 8
-        - seed: 42
-        - 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: 200
-        - num_epochs: 50
-        - mixed_precision_training: Native AMP         # Optional. Example for BLEU: max_order
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -60,17 +15,21 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-urdu-urm-60](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-urdu-urm-60) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.4593
-- Wer: 0.5772
-- Cer: 0.3384
+- Loss: 9.8476
+- Wer: 0.6253
+- Cer: 0.3456
 
 ## Model description
 
-The training and valid dataset is 0.58 hours. It was hard to train any model on lower number of so I decided to take Urdu checkpoint and finetune the XLSR model.
+More information needed
+
+## Intended uses & limitations
+
+More information needed
 
 ## Training and evaluation data
 
-Trained on Harveenchadha/vakyansh-wav2vec2-urdu-urm-60 due to lesser number of samples. Persian and Urdu are quite similar. 
+More information needed
 
 ## Training procedure
 
@@ -86,19 +45,16 @@ 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: 200
-- num_epochs: 50
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 13.2136       | 8.33  | 100  | 9.5424          | 0.7672 | 0.4381 |
-| 2.6996        | 16.67 | 200  | 8.4317          | 0.6661 | 0.3620 |
-| 1.371         | 25.0  | 300  | 9.5518          | 0.6443 | 0.3701 |
-| 0.639         | 33.33 | 400  | 9.4132          | 0.6129 | 0.3609 |
-| 0.4452        | 41.67 | 500  | 10.8330         | 0.5920 | 0.3473 |
-| 0.3233        | 50.0  | 600  | 11.4593         | 0.5772 | 0.3384 |
+| 13.7919       | 8.33  | 100  | 7.9423          | 0.6742 | 0.3737 |
+| 1.4283        | 16.67 | 200  | 3.2921          | 0.6681 | 0.3707 |
+| 0.4868        | 25.0  | 300  | 9.8476          | 0.6253 | 0.3456 |
 
 
 ### Framework versions