arturslogins
/

whisper-medium-lv

Automatic Speech Recognition

hf-asr-leaderboard

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

arturslogins commited on May 7

Commit

58a7e4a

•

1 Parent(s): 6bc98c4

End of training

Files changed (2) hide show

README.md +11 -11
training_log.txt +2 -2

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 43.705463182897866
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [arturslogins/whisper-medium-lv](https://huggingface.co/arturslogins/whisper-medium-lv) on the Recorded Voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0843
-- Wer: 43.7055
 ## Model description
@@ -69,18 +69,18 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0097        | 6.3898  | 1000 | 0.9780          | 45.8432 |
-| 0.0023        | 12.7796 | 2000 | 1.0158          | 44.9525 |
-| 0.0002        | 19.1693 | 3000 | 1.0549          | 46.1758 |
-| 0.0001        | 25.5591 | 4000 | 1.0765          | 44.9881 |
-| 0.0001        | 31.9489 | 5000 | 1.0843          | 43.7055 |
 ### Framework versions
 - Transformers 4.41.0.dev0
 - Pytorch 2.0.1
-- Datasets 2.19.0
 - Tokenizers 0.19.1

     metrics:
     - name: Wer
       type: wer
+      value: 31.294536817102138
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [arturslogins/whisper-medium-lv](https://huggingface.co/arturslogins/whisper-medium-lv) on the Recorded Voice dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4217
+- Wer: 31.2945
 ## Model description
 ### Training results
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.1818        | 0.1867 | 1000 | 0.5788          | 36.5321 |
+| 0.1331        | 0.3734 | 2000 | 0.5003          | 33.9311 |
+| 0.097         | 0.5601 | 3000 | 0.4944          | 36.2470 |
+| 0.0809        | 0.7468 | 4000 | 0.4433          | 32.3515 |
+| 0.1434        | 0.9334 | 5000 | 0.4217          | 31.2945 |
 ### Framework versions
 - Transformers 4.41.0.dev0
 - Pytorch 2.0.1
+- Datasets 2.19.1
 - Tokenizers 0.19.1

training_log.txt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aefd65502e43b27bb26cd84099ea3b1ac7bfeb8e61c8ce32e10eaebd2986868
-size 11779479

 version https://git-lfs.github.com/spec/v1
+oid sha256:5e214c9ccb562dd58ba4d3c204f05e23530ec1e0acc9a390ebc3b4ff18edb2fd
+size 11794320