Training in progress, step 4000

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-large-v3](https://huggingface.co/openai/whisper-large-v3) on the JacobLinCool/common_voice_19_0_zh-TW dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1491
-- eval_wer: 145.4419
-- eval_cer: 184.9172
-- eval_decode_runtime: 106.8166
-- eval_wer_runtime: 0.1310
-- eval_cer_runtime: 0.2072
-- eval_runtime: 351.3592
-- eval_samples_per_second: 14.267
-- eval_steps_per_second: 0.447
-- epoch: 2.0825
-- step: 3500
+- eval_loss: 0.1502
+- eval_wer: 253.4012
+- eval_cer: 234.4286
+- eval_decode_runtime: 107.4219
+- eval_wer_runtime: 0.1395
+- eval_cer_runtime: 0.2215
+- eval_runtime: 352.6335
+- eval_samples_per_second: 14.216
+- eval_steps_per_second: 0.445
+- epoch: 2.1825
+- step: 4000
 
 ## Model description
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d90cb5f93f98a27f53258b9c22cb536cd0536c2419c3302a0f0949a45057a3b
+oid sha256:0f155746d6809698daf3f1d59e5da0976d4806378f970a2e3c4cf8ca026d2cdb
 size 230831688

runs/Oct31_07-56-37_24a46c0bfe1b/events.out.tfevents.1730361815.24a46c0bfe1b.773.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb2810b49de9e9cac9817aa5d00404b55801954b4dbd9d87a8a7bce462d143f
-size 4171023
+oid sha256:4ad7902864b92e3e000683a657dea2d117bac00b1d9414483e13073c2b8a38d6
+size 4726428