End of training

README.md

@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5819
-- eval_wer: 0.6181
-- eval_runtime: 42.4804
-- eval_samples_per_second: 2.354
-- eval_steps_per_second: 0.165
-- epoch: 2.9330
-- step: 3000
+- eval_loss: 0.4051
+- eval_wer: 0.4848
+- eval_runtime: 42.6897
+- eval_samples_per_second: 2.342
+- eval_steps_per_second: 0.164
+- epoch: 5.3765
+- step: 5500
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490da23ce0bccb36c599d9b41e37ed2c74d6323bc34f8f4271e70993f53f8a2c
+oid sha256:593c407596fcb138c5928b746e0d85c377341890b8251e8c06139033715d0c54
 size 37789960

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba7664cf1ce902df2bb51a4874b939042d7a97ca28d77fc03525ba2c0e0e18b
+oid sha256:e1f265d4e8c42c7f135192f2e69a6623667185e17fa2c35c7797097edd0c9b57
 size 5432