GroupSix/whisper-small-sv

README.md

@@ -17,8 +17,8 @@ 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:
-- Loss: 0.3121
-- Wer: 103.0031
+- Loss: 0.2908
+- Wer: 55.7146
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -53,8 +53,6 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
 | 0.1253        | 1.28  | 1000 | 0.2983          | 129.5722 |
 | 0.0616        | 2.55  | 2000 | 0.2908          | 55.7146  |
-| 0.0297        | 3.83  | 3000 | 0.3023          | 74.1704  |
-| 0.0066        | 5.11  | 4000 | 0.3121          | 103.0031 |
 
 
 ### Framework versions

runs/Dec06_12-35-05_a6a990a2db63/events.out.tfevents.1701866152.a6a990a2db63.1391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e5cf9e27d5357419cd7d8dd0efb1920f4dbcf3a746fee771938d96de5bfb29
+size 5672

runs/Dec06_13-08-45_f362f33f3ebf/events.out.tfevents.1701868211.f362f33f3ebf.782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3646cd9e41793e1747027c21444526ee057bd98a7a0a16a26851752e0464ded
+size 5672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f990da40c94080e87a5282b489f2d9ad90725175f33df073645d07b6b6a533c
+oid sha256:e1c4936a8467877044076c036c538d550326a798628ef92092f11c8a02e4280c
 size 4920