End of training

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0417
-- eval_cer: 1.4726
-- eval_runtime: 1033.0376
-- eval_samples_per_second: 4.413
-- eval_steps_per_second: 0.138
+- eval_loss: 0.0620
+- eval_cer: 2.8955
+- eval_runtime: 582.5363
+- eval_samples_per_second: 7.826
+- eval_steps_per_second: 0.245
 - step: 0
 
 ## Model description
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 64
 - eval_batch_size: 32
 - seed: 42

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e02ab59fc94e9b47d4b163f03c542f1257531276ed4f5742863ec34f8319fb9
+oid sha256:a7136a8d7fb10c4bc95625a155d564874c8e8404bc3f41d611863f45ba70b311
 size 151061672

runs/Aug15_03-36-20_nv3090/events.out.tfevents.1723664762.nv3090.320278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f671e3af9ac07cfa53f2799946cc0d598a59311737a68629f9baf9cfc855449
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6840e5deb41fc1bea3852338c228988fafaeea0f9fdd20640885869186ce022
+oid sha256:c2511beb8e0a742a5d8b9e6ea7686a6de2c85e30804f44e1ee3dfb62465b322f
 size 5304