update model card README.md

README.md

@@ -1,31 +1,35 @@
 ---
 language:
 - el
-license: apache-2.0
 tags:
-- whisper-medium
-- mozilla-foundation/common_voice_11_0
-- greek
-- whisper-event
-- hf-asr-leaderboard
+- hf-asr-leaderboard, whisper-large, mozilla-foundation/common_voice_11_0, greek,
+  whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_11_0
+- mozilla-foundation/common_voice_11_0, google/fleurs
 model-index:
-- name: Whisper medium El - Greek One
+- name: Whisper Medium El - Greek One
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper medium El - Greek One
+# Whisper Medium El - Greek One
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/medium-small](https://huggingface.co/openai/medium-small) on the Common Voice 11.0 dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.3928
+- eval_wer: 14.8031
+- eval_runtime: 1229.0439
+- eval_samples_per_second: 1.38
+- eval_steps_per_second: 0.172
+- epoch: 20.0
+- step: 1000
 
 ## Model description
 
-This is a fine-tuned version of the medium whisper model for Greek language.
+More information needed
 
 ## Intended uses & limitations
 
@@ -41,20 +45,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
+- train_batch_size: 20
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 40
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 12000
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.25.0.dev0
-- Pytorch 1.13.0
-- Datasets 2.6.1
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.0+cu116
+- Datasets 2.7.1.dev0
 - Tokenizers 0.13.2