Training in progress, step 100

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 common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 5.1640
-- eval_wer: 125.6250
-- eval_runtime: 27.1811
-- eval_samples_per_second: 0.736
-- eval_steps_per_second: 0.037
-- epoch: 24.03
-- step: 75
+- eval_loss: 5.0878
+- eval_wer: 128.125
+- eval_runtime: 27.4776
+- eval_samples_per_second: 0.728
+- eval_steps_per_second: 0.036
+- epoch: 33.01
+- step: 100
 
 ## Model description
 

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f3a809d2a1c7f7b6de05eeeec792a49857ee658565c60774979f52a699403c
+oid sha256:dc272cb1284b8a10b707954b8162c37d4b6d437fd6fb91a2c9a2431d9f0a6636
 size 14208970