Training in progress, step 60

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: 0.4493
-- eval_wer: 16.5354
-- eval_cer: 88.1392
-- eval_decode_time: 0.5203
-- eval_wer_time: 0.0054
+- eval_loss: 0.2922
+- eval_wer: 8.2677
+- eval_cer: 97.5852
+- eval_decode_time: 0.5434
+- eval_wer_time: 0.0060
 - eval_cer_time: 0.0032
-- eval_runtime: 1.3178
-- eval_samples_per_second: 7.588
-- eval_steps_per_second: 1.518
-- epoch: 2.12
-- step: 50
+- eval_runtime: 1.3214
+- eval_samples_per_second: 7.568
+- eval_steps_per_second: 1.514
+- epoch: 3.03
+- step: 60
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b449598bad47929b0ce7ce9703863717369e58b5e614b756d22f3d1ac8a9ba
+oid sha256:042e0c3a918c14b727dcfc1ea925b2d3c7674a5622906b94464180e5e38cf6fe
 size 8668296

runs/Oct31_02-35-20_JacobdeMacBook-Pro.local/events.out.tfevents.1730313339.JacobdeMacBook-Pro.local.87069.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dc001a5b0261bac911f6a48482fb441eeb2badbf03d4ee1bd67129b6ecfc70e
-size 39347
+oid sha256:e75d5e74b7dd4afc73c4784c8dbfe2c5fc553fa6c52fbf1971ea220da8625e3f
+size 46327