Model save

README.md

@@ -1,7 +1,5 @@
 ---
-base_model: KevinKibe/whisper-medium-finetuned
-datasets:
-- common_voice_16_1
+base_model: openai/whisper-medium
 library_name: peft
 license: apache-2.0
 tags:
@@ -14,17 +12,19 @@ model-index:
 <!-- 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. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/hv5p2q4p)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/keviinkibe/huggingface/runs/hv5p2q4p)
 # whisper-medium-finetuned-finetuned
 
-This model is a fine-tuned version of [KevinKibe/whisper-medium-finetuned](https://huggingface.co/KevinKibe/whisper-medium-finetuned) on the common_voice_16_1 dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.1774
-- eval_wer: 77.2386
-- eval_runtime: 382.2171
-- eval_samples_per_second: 0.654
-- eval_steps_per_second: 0.042
-- epoch: 1.37
-- step: 100
+- eval_loss: 5.4740
+- eval_wer: 103.4838
+- eval_runtime: 542.8842
+- eval_samples_per_second: 0.461
+- eval_steps_per_second: 0.059
+- epoch: 0.25
+- step: 500
 
 ## Model description
 
@@ -43,19 +43,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.001
+- train_batch_size: 32
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 100
+- lr_scheduler_warmup_steps: 20
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.39.2
+- Transformers 4.42.3
 - Pytorch 2.2.2+cu121
 - Datasets 2.19.2
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1