Model save

README.md

@@ -1,9 +1,11 @@
 ---
-license: apache-2.0
+base_model: openai/whisper-small
+datasets:
+- common_voice_16_1
 library_name: peft
+license: apache-2.0
 tags:
 - generated_from_trainer
-base_model: openai/whisper-small
 model-index:
 - name: whisper-small-finetuned
   results: []
@@ -12,19 +14,19 @@ 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/zbv26o2q)
-[<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/zbv26o2q)
+[<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/h79p39mv)
+[<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/h79p39mv)
 # whisper-small-finetuned
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.2990
-- eval_wer: 94.3081
-- eval_runtime: 602.9832
-- eval_samples_per_second: 0.415
-- eval_steps_per_second: 0.053
-- epoch: 0.25
-- step: 500
+- eval_loss: 4.5110
+- eval_wer: 134.4828
+- eval_runtime: 13.445
+- eval_samples_per_second: 0.744
+- eval_steps_per_second: 0.074
+- epoch: 4.1
+- step: 10
 
 ## Model description
 
@@ -43,14 +45,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 32
-- eval_batch_size: 8
+- learning_rate: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 20
-- training_steps: 2000
+- training_steps: 20
 - mixed_precision_training: Native AMP
 
 ### Framework versions