Training in progress, step 20

README.md

@@ -20,13 +20,13 @@ 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 common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.1314
-- eval_wer: 31.1628
-- eval_runtime: 127.0315
+- eval_loss: 2.8648
+- eval_wer: 29.3023
+- eval_runtime: 127.6201
 - eval_samples_per_second: 0.157
 - eval_steps_per_second: 0.024
-- epoch: 3.0333
-- step: 10
+- epoch: 6.0667
+- step: 20
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4bcc45e6a8da2ae160f9bd65758048abe4faf10b4343a1aedbe1bf55f148e2
+oid sha256:a0f7f89896d2703bc2e4070c3629a405e72f4485fb6e708f507cd4b96b50ff5e
 size 62969640