Training in progress, step 2000

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.1420
-- eval_wer: 77.8705
-- eval_runtime: 457.3267
-- eval_samples_per_second: 0.547
-- eval_steps_per_second: 0.07
-- epoch: 2.125
-- step: 1500
+- eval_loss: 1.8218
+- eval_wer: 76.6438
+- eval_runtime: 467.7839
+- eval_samples_per_second: 0.534
+- eval_steps_per_second: 0.068
+- epoch: 3.0625
+- step: 2000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c42de71eb3d37c7f82fe1a6f50ce56b6f78cf7f4cdc6cd90d8056258aafc8e7
+oid sha256:b05f2957043008b1eee5aaa3d634bc33a505306590c293109784dd0919494fdf
 size 14176064