Update README.md

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hamsa-medium
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the nadsoft/Jordan-Audio dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) using [ARBML](https://github.com/ARBML/whisperar) on the [**nadsoft/Jordan-Audio dataset.**](https://huggingface.co/datasets/nadsoft/Jordan-Audio)
 
 ## Model description
 
-More information needed
+Hamsa is a Whisper Medium model that has been fine-tuned using the ARBML method in this repository. We have also added some Jordanian data to the model to adapt it to a few shot learning tasks.
 
 ## Intended uses & limitations
 
@@ -27,32 +27,9 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+ nadsoft/Jordan-Audio
 
 ## Training procedure
 
 ### Training hyperparameters
 
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 32
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 50
-- training_steps: 10
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
-| No log        | 0.07  | 10   | 3.0803          | 0.4207    | 0.3471 |
-
-
-### Framework versions
-
-- Transformers 4.34.1
-- Pytorch 2.1.0+cu118
-- Datasets 2.14.5
-- Tokenizers 0.14.1