Samandards/uzbek-5k-data

README.md

@@ -7,8 +7,6 @@ tags:
 model-index:
 - name: temp
   results: []
-language:
-- uz
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,7 +16,7 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7821
+- Loss: 0.7851
 
 ## Model description
 
@@ -51,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0652        | 1.0   | 86   | 0.9028          |
-| 0.6926        | 2.0   | 172  | 0.7821          |
+| 1.0755        | 1.0   | 86   | 0.9188          |
+| 0.7077        | 2.0   | 172  | 0.7851          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4798de16772b7209d4015a76168294196717d7cf53efa50c1c01278a73fca20b
+oid sha256:a451fe719a2420242edc60db797e71663841018892bff7ed08a276e5cc52b5af
 size 7918280

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848d29ca659656cfadb73a102759a84e4bd0a59d31c48a96b2fa1b935abda895
+oid sha256:2bc4646ccee0d1bfb5d6bfe7034c66d689a3f32ba52e17ac5759f73a14b43d36
 size 5304