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](https://huggingface.co/openai/whisper-large-v3) on the JacobLinCool/ami-disfluent dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1298
-- eval_wer: 35.1729
-- eval_cer: 45.0300
-- eval_decode_runtime: 145.3294
-- eval_wer_runtime: 0.0786
-- eval_cer_runtime: 0.1310
-- eval_runtime: 230.9848
-- eval_samples_per_second: 8.191
-- eval_steps_per_second: 0.26
-- epoch: 2.276
-- step: 900
+- eval_loss: 0.1300
+- eval_wer: 32.3225
+- eval_cer: 45.5147
+- eval_decode_runtime: 141.5643
+- eval_wer_runtime: 0.1227
+- eval_cer_runtime: 0.2049
+- eval_runtime: 227.2773
+- eval_samples_per_second: 8.325
+- eval_steps_per_second: 0.264
+- epoch: 3.064
+- step: 1000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617a5686040972aed042db1fdca523cd6d1a972345b92a8f108a1960a331323c
+oid sha256:d3ca2c6080b9e7fcdabf28a6808ddf13761616414fd83ddf8a5e883b0865419a
 size 230831688

runs/Jan16_20-41-06_5d04024295f3/events.out.tfevents.1737060251.5d04024295f3.3416.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5781da58f0ed6fe30f55d4158f38b81e14a5887f2ddbc14c7d6310aff1a8dff
-size 4472919
+oid sha256:39cd8f00f2aea43387fa810dc03bc4dd4a39a6b47a5fe194bce8efeaf5eaba82
+size 4837576