Training in progress, step 28

README.md

@@ -25,17 +25,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the ntnu-smil/sandi2025-ds dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.0601
-- eval_wer: 84.5443
-- eval_cer: 211.8357
-- eval_decode_runtime: 295.8525
-- eval_wer_runtime: 0.2329
-- eval_cer_runtime: 0.5515
-- eval_runtime: 779.9936
-- eval_samples_per_second: 4.165
+- eval_loss: 1.0265
+- eval_wer: 80.7774
+- eval_cer: 205.4415
+- eval_decode_runtime: 296.9575
+- eval_wer_runtime: 0.2339
+- eval_cer_runtime: 0.5476
+- eval_runtime: 780.8954
+- eval_samples_per_second: 4.161
 - eval_steps_per_second: 0.131
-- epoch: 3.1071
-- step: 21
+- epoch: 4.1429
+- step: 28
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac6b8da4684edfaced2580a02ae30863e5637d76bc03cccf4ae82bb55444f6f
+oid sha256:2fe20cc837184f88a9ec19e3a9697b4cdf2d9f9aeda7ca64f43a6c612cbbaa43
 size 230831688

runs/Mar30_07-28-31_27bdf695dc8e/events.out.tfevents.1743319991.27bdf695dc8e.2945.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fea49920341ddfba975a52633e2aed1a6669c64fa949bdf6943190234ea7350
-size 9246757
+oid sha256:de8e402679bbc2eb120edfc005f526595553cf001fcc0f8f33a9c31535f2b7dc
+size 12336311