End of training

README.md

@@ -19,11 +19,11 @@ 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 TAT ASR Aligned dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5107
-- eval_cer: 8.3425
-- eval_runtime: 1249.1161
-- eval_samples_per_second: 4.496
-- eval_steps_per_second: 0.141
+- eval_loss: 0.4231
+- eval_cer: 9.3916
+- eval_runtime: 1392.366
+- eval_samples_per_second: 4.033
+- eval_steps_per_second: 0.126
 - step: 0
 
 ## Model description

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-tiny_tat/checkpoint-6810",
+  "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-tiny_tat/checkpoint-3405",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb9b77ce7a6d6b9faad41352cd046bde294414b49366d6ea10fbe07a2b388bf
+oid sha256:01b4053dc8c86bcaabe40ebd2e7f5f14d03f428f0aa57583b36361513d965d5c
 size 151061672

runs/Sep01_23-12-37_SOTA/events.out.tfevents.1725204957.SOTA.1389671.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88486a8d48c48d480529f57f93356570a4f841bfe72c5b6d8a1941aa130edea
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4fde17c9de8b1cb557fd3b4b9ed5982d6483593a7680756c2d27a26a911ff63
+oid sha256:c6f776fe79f27e14d957d2d0bf09be0aaa4a3a0554ac117cfda0a8ce11832b98
 size 5368