Update README.md

README.md

@@ -4,9 +4,26 @@ tags:
 - generated_from_trainer
 model-index:
 - name: wav2vec2-tiny-random-rodela-classifier
-  results: []
+  results:
+    - task:
+        type: audio-classification
+      dataset:
+        name: rodela_dataset
+        type: test
+      metrics:
+        - name: accuracy
+          type: accuracy
+          value: 0.91
+        
 datasets:
 - shhossain/rodela_dataset
+license: apache-2.0
+language:
+- be
+- en
+metrics:
+- accuracy
+pipeline_tag: audio-classification
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-tiny-random-rodela-classifier
 
-This model is a fine-tuned version of [patrickvonplaten/wav2vec2_tiny_random](https://huggingface.co/patrickvonplaten/wav2vec2_tiny_random) on an unknown dataset.
+This model is a fine-tuned version of [patrickvonplaten/wav2vec2_tiny_random](https://huggingface.co/patrickvonplaten/wav2vec2_tiny_random) on [shhossain/rodela_dataset](https://huggingface.co/datasets/shhossain/rodela_dataset) dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.7650
 - eval_accuracy: 0.9102
@@ -26,15 +43,12 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+It classifies if a audio has `rodela` in it.
 
 ## Intended uses & limitations
 
-More information needed
+It was designed for `Wake Word Detection`.
 
-## Training and evaluation data
-
-More information needed
 
 ## Training procedure
 
@@ -50,6 +64,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 100
+- gradient_accumulation_steps: .5
 
 ### Framework versions