Training in progress, step 3000

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: 2.1747
-- eval_wer: 98.6261
-- eval_runtime: 692.0594
-- eval_samples_per_second: 0.361
-- eval_steps_per_second: 0.046
-- epoch: 1.0312
-- step: 2000
+- eval_loss: 1.8724
+- eval_wer: 78.8027
+- eval_runtime: 475.0113
+- eval_samples_per_second: 0.526
+- eval_steps_per_second: 0.067
+- epoch: 1.2812
+- step: 3000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc550acd80bcd741bcc0d7908287dc89a185c2b01d3b86170bc945df658cf9e
+oid sha256:16e7bb149544c107679749850ba36af40cb0a84bb38f557965a735f10db0a2a6
 size 14176064