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: 0.0413
-- eval_cer: 1.4368
-- eval_runtime: 1087.1917
-- eval_samples_per_second: 4.193
-- eval_steps_per_second: 0.132
+- eval_loss: 0.0595
+- eval_cer: 2.9417
+- eval_runtime: 588.6394
+- eval_samples_per_second: 7.745
+- eval_steps_per_second: 0.243
 - 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_03-25-36_nv3090/events.out.tfevents.1723664125.nv3090.319767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea95bc3b775023d26eb63b5966503db5ae95db72e292480beebd813cb4f8bbde
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63772f5dc6081699fbdb0ab87a262d4d0d30585d1beb7255af525ccb96f165b0
+oid sha256:3f8e272fdfbfd1011da730f5b231b6c45a837f681c0a38e447bec1ff7a8e6898
 size 5304