End of training

README.md

@@ -1,13 +1,13 @@
 ---
-base_model: openai/whisper-large-v3
 language:
 - rus
 license: apache-2.0
-metrics:
-- wer
+base_model: openai/whisper-large-v3
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: Whisper Large V3 rus pl - Chee Li
   results: []
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Google Fleurs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1165
-- Wer: 108.0475
+- Loss: 0.1164
+- Wer: 98.5381
 
 ## Model description
 
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer      |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 0.0324        | 2.6178  | 1000 | 0.0814          | 73.6269  |
-| 0.0058        | 5.2356  | 2000 | 0.1047          | 117.0652 |
-| 0.0033        | 7.8534  | 3000 | 0.1141          | 126.9367 |
-| 0.0022        | 10.4712 | 4000 | 0.1165          | 108.0475 |
+| 0.0324        | 2.6178  | 1000 | 0.0814          | 70.5971  |
+| 0.0058        | 5.2356  | 2000 | 0.1047          | 117.8747 |
+| 0.0033        | 7.8534  | 3000 | 0.1139          | 120.5834 |
+| 0.0022        | 10.4712 | 4000 | 0.1164          | 98.5381  |
 
 
 ### Framework versions

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea19cf0d9768cea21dcdf235e8d98a4e2512f48880ed15de8c06989e359220b4
+oid sha256:d9c571ca88ff4bd2f13c773c5450ec984249388ea4e9044af6d6db2ec6a566c2
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778cbfa6517216f155eb66b0d2b38e9872666420dc7ae9a33b0efa03b777c7bb
+oid sha256:c00d83a6357679adab7ba450b1b3fd3bf43b1397b71553bb8d9062e722ebddef
 size 1180663192