Fine-tuned Whisper model for Vietnamese - Step 1000

README.md

@@ -16,13 +16,13 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.9681
-- eval_wer: 0.5913
-- eval_runtime: 2852.3107
-- eval_samples_per_second: 2.038
-- eval_steps_per_second: 0.255
-- epoch: 0.1599
-- step: 16000
+- eval_loss: 1.3997
+- eval_wer: 0.7495
+- eval_runtime: 5201.1699
+- eval_samples_per_second: 1.118
+- eval_steps_per_second: 0.14
+- epoch: 0.0100
+- step: 1000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd50861b217a6747aff463a4541cc9e2ef7ee5085c38d67bf9c4756b59726fc
+oid sha256:55f21755a1661fb77b6bc1d7a77264ca007b2139c1277b01b2522c852f4173dd
 size 151061672

runs/Nov06_09-09-20_ubuntu/events.out.tfevents.1762420174.ubuntu.3277758.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cb3006354fa86b0bfcd8f59c7820ad40da613b666efbbd096ba21f1de04949
-size 3386407
+oid sha256:cf793c96552fd51365b04e3e2503f9714ffe2c4cac2d58dd27016eb5c7517e4a
+size 3599875

runs/Nov12_04-40-06_ubuntu/events.out.tfevents.1762922409.ubuntu.1799592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a77757766e4cce0df8cb9615b580d0c3d3748f35251196f222c1de1ca3bdf5
+size 216637

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc5d72510cbbb5949e9afeaa30eb42ec514e8cd65547fc51b0dc33273228cd5
+oid sha256:7abdb17c6a288aa56cf8cbfc89e8e74b6e19941c3159f6be684c200e047ba867
 size 5496