End of training

README.md

@@ -25,17 +25,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the hf-internal-testing/librispeech_asr_dummy dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.1646
-- eval_wer: 258.2677
-- eval_cer: 100.0
-- eval_decode_time: 0.5213
-- eval_wer_time: 1.4057
-- eval_cer_time: 0.0046
-- eval_runtime: 2.7415
-- eval_samples_per_second: 3.648
-- eval_steps_per_second: 0.73
-- epoch: 1.01
-- step: 20
+- eval_loss: 0.8100
+- eval_wer: 37.7953
+- eval_cer: 52.3438
+- eval_decode_time: 0.5008
+- eval_wer_time: 0.0396
+- eval_cer_time: 0.0045
+- eval_runtime: 2.1555
+- eval_samples_per_second: 4.639
+- eval_steps_per_second: 0.928
+- epoch: 1.11
+- step: 30
 
 ## Model description