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: 0.0568
-- eval_cer: 2.5256
-- eval_runtime: 1031.73
-- eval_samples_per_second: 4.419
-- eval_steps_per_second: 0.139
+- eval_loss: 0.0824
+- eval_cer: 4.0964
+- eval_runtime: 589.9301
+- eval_samples_per_second: 7.728
+- eval_steps_per_second: 0.242
 - 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_03-13-48_nv3090/events.out.tfevents.1723663418.nv3090.319248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad9d6c6f53f05b44b9c0167745eb5c8ab76b3639bfb995a322544131b72f3f7
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14aa37c71a9a1a0b882d9f063fd81f33ed887ac4053e7038fd4ef0e42980c8f5
+oid sha256:a48fc87e8318d77fffa9c18d8c7edba11fe92faa79bc4d2591ba3f93d957cea8
 size 5304