carlot
/

whisper-base-mixedv1.4

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

carlot commited on Dec 5, 2023

Commit

9053980

•

1 Parent(s): 1597ba4

carlot/whisper-base-mixedv1.4

Files changed (2) hide show

README.md +6 -6
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model was trained from scratch on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7537
-- Cer: 22.6185
 ## Model description
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0233        | 8.55  | 1000 | 0.7019          | 23.3224 |
-| 0.0027        | 17.09 | 2000 | 0.7418          | 23.0408 |
-| 0.0016        | 25.64 | 3000 | 0.7455          | 22.8531 |
-| 0.0002        | 34.19 | 4000 | 0.7537          | 22.6185 |
 ### Framework versions

 This model was trained from scratch on the audiofolder dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3061
+- Cer: 9.5109
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0363        | 8.85  | 1000 | 0.3010          | 10.1630 |
+| 0.0003        | 17.7  | 2000 | 0.2905          | 9.1304  |
+| 0.0003        | 26.55 | 3000 | 0.3068          | 9.0217  |
+| 0.0001        | 35.4  | 4000 | 0.3061          | 9.5109  |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b1b8d76f2962bf371af51f27d0b735d0c028104a63eddb0eb3b6f8ea7695d9
 size 290403936

 version https://git-lfs.github.com/spec/v1
+oid sha256:b712b1af000bd990f16b0a748761b3c4b95935e9dad507e5d25afa3c2eb5ea8a
 size 290403936