Training in progress, step 1000

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-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the JacobLinCool/ami-disfluent dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1462
-- eval_wer: 7.7887
-- eval_cer: 3.2604
-- eval_decode_runtime: 110.7694
-- eval_wer_runtime: 0.0710
-- eval_cer_runtime: 0.0937
-- eval_runtime: 185.3196
-- eval_samples_per_second: 10.209
+- eval_loss: 0.1459
+- eval_wer: 7.7269
+- eval_cer: 3.2519
+- eval_decode_runtime: 111.0004
+- eval_wer_runtime: 0.0705
+- eval_cer_runtime: 0.0932
+- eval_runtime: 185.4061
+- eval_samples_per_second: 10.205
 - eval_steps_per_second: 0.324
-- epoch: 2.276
-- step: 900
+- epoch: 3.064
+- step: 1000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686b5417f31bdd7bdd58c4ae8f0c3ba8bbbb852b56f3339d511af933402f98a3
+oid sha256:f0870a9c2b9de6f73fe5d749f88f793e770237b17e8fb4e563a660b709ae905d
 size 111475752

runs/Jan15_20-47-10_72fee014ddc5/events.out.tfevents.1736974043.72fee014ddc5.46395.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e4060c501cb2b5f2eed74a9cb7ea522a272b34b3e913d82e6eff6b0558c992
-size 2817224
+oid sha256:7587aa013a77d7118da179d403fe79c1b7234b9d65c5308a0b3734192241a6fa
+size 3090696