Training in progress, step 20

README.md

@@ -4,7 +4,7 @@ base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- common_voice_16_1
+- common_voice_17_0
 library_name: peft
 model-index:
 - name: whisper-small-finetuned
@@ -14,19 +14,21 @@ 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/albertusgeyser-private-email/huggingface/runs/8lqmabgc)
+[<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/albertusgeyser-private-email/huggingface/runs/8lqmabgc)
 [<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/albertusgeyser-private-email/huggingface/runs/8lqmabgc)
 [<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/albertusgeyser-private-email/huggingface/runs/8lqmabgc)
 # whisper-small-finetuned
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_16_1 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.5505
-- eval_wer: 64.6512
-- eval_runtime: 21.4566
-- eval_samples_per_second: 0.932
-- eval_steps_per_second: 0.093
-- epoch: 49.02
-- step: 100
+- eval_loss: 3.5415
+- eval_wer: 66.0465
+- eval_runtime: 16.3765
+- eval_samples_per_second: 1.221
+- eval_steps_per_second: 0.061
+- epoch: 19.01
+- step: 20
 
 ## Model description
 
@@ -46,8 +48,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830d8ee2b1b1f94f1a7941f1e4e9bae2ff30d05c07dd73a79555f724e861ab57
+oid sha256:f06633a358af1220e4e21f5e16eeac6780bb931777317dc9ac95234706f0b121
 size 14176064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd39c6bd920a38ea9bb5ac4cb1c018fb7b12659da23b058281b33b9f9d5a540
+oid sha256:4e9c0f990cd62c4a314194f8df86f013fa125a968b85201927e1c9b01694c489
 size 5368