faster-whisper-small-nya-tknEN

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-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.6823
-- eval_wer: 0.3086
-- eval_cer: 0.0879
-- eval_runtime: 184.5114
-- eval_samples_per_second: 3.122
-- eval_steps_per_second: 0.39
-- epoch: 15.1733
+- eval_loss: 0.5583
+- eval_wer: 0.3817
+- eval_cer: 0.1696
+- eval_runtime: 258.7829
+- eval_samples_per_second: 2.404
+- eval_steps_per_second: 0.301
+- epoch: 8.6621
 - step: 2200
 
 ## Model description
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- training_steps: 5000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6787e0d868bc2d6a4e787951d6477ffba7ba5c8ac7102eb4f012fee6871ce49d
+oid sha256:5cfbfffc70d72c26881529282becd5ed28239d79c1030c2e604ad528e6b39829
 size 966995080

runs/Oct25_10-24-45_0fda9ea3c11a/events.out.tfevents.1761387888.0fda9ea3c11a.703.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d03ae0c7c66d16944135161f21ab732ffece3e120acf7f4e7293ecf3b60757
+size 20050

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68fd019290cc883b362574267129fa639acf50f97b9cf5cf27d05a0821259be4
+oid sha256:48ad6fbcdc07081456b07bf1623eb091788258f477313dce9ab172ef6f2090c6
 size 5969