Simonom/uzbek-stt-v2-3k-data

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_14_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6899
+- Loss: 0.6938
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8857        | 1.0   | 189  | 0.7888          |
-| 0.5781        | 2.0   | 378  | 0.6899          |
+| 0.8861        | 1.0   | 189  | 0.7931          |
+| 0.5809        | 2.0   | 378  | 0.6938          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276851e435ed059c7165e0f9d81dc4b3fb05ca8dacd6a77162852bfbf42413be
+oid sha256:47d6f931bab68e449a5f041b7b521fe6147eba1f59b2d3bdaef1ba2fffe180f0
 size 62976168

runs/Jun01_08-14-40_05db13909f2b/events.out.tfevents.1717229681.05db13909f2b.448.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a83423330a8023e7231cbe2be6ba010c10875afe5d4757d61b0ce4e9e6b743
+size 10177

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4294fc7ebd466924228624b535f6860df0af48cf742258cdafb156230b6543
+oid sha256:fe94d8a6fe9a79bc68aa0ff884729f1068cb3d5495d760d00e016f711b1a0155
 size 5240