Commit
•
50aeb48
1
Parent(s):
994d58f
End of training
Browse files
README.md
CHANGED
|
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 and the Common Voice 15.0 datasets.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Cer:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -47,18 +47,24 @@ The following hyperparameters were used during training:
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 100
|
| 50 |
-
- num_epochs:
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|
| 56 |
-
| 0.7938 | 0.16 | 500 | 0.7768 |
|
| 57 |
-
| 0.5845 | 0.32 | 1000 | 0.5947 |
|
| 58 |
-
| 0.459 | 0.48 | 1500 | 0.5132 |
|
| 59 |
-
| 0.3512 | 0.64 | 2000 | 0.4709 |
|
| 60 |
-
| 0.3758 | 0.8 | 2500 | 0.4363 |
|
| 61 |
-
| 0.3191 | 0.96 | 3000 | 0.4216 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 and the Common Voice 15.0 datasets.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.3736
|
| 24 |
+
- Cer: 29.6973
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- num_epochs: 2
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:-------:|:---------------:|
|
| 56 |
+
| 0.7938 | 0.16 | 500 | 55.8341 | 0.7768 |
|
| 57 |
+
| 0.5845 | 0.32 | 1000 | 41.1522 | 0.5947 |
|
| 58 |
+
| 0.459 | 0.48 | 1500 | 37.6183 | 0.5132 |
|
| 59 |
+
| 0.3512 | 0.64 | 2000 | 35.4047 | 0.4709 |
|
| 60 |
+
| 0.3758 | 0.8 | 2500 | 33.5778 | 0.4363 |
|
| 61 |
+
| 0.3191 | 0.96 | 3000 | 32.6110 | 0.4216 |
|
| 62 |
+
| 0.2295 | 1.13 | 3500 | 0.4261 | 32.4977 |
|
| 63 |
+
| 0.1806 | 1.29 | 4000 | 0.4085 | 31.9909 |
|
| 64 |
+
| 0.16 | 1.45 | 4500 | 0.3913 | 31.1708 |
|
| 65 |
+
| 0.1603 | 1.61 | 5000 | 0.3836 | 30.3841 |
|
| 66 |
+
| 0.1343 | 1.77 | 5500 | 0.3784 | 30.1574 |
|
| 67 |
+
| 0.1265 | 1.93 | 6000 | 0.3736 | 29.6973 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
runs/Apr12_11-44-16_77266c735848/events.out.tfevents.1712922285.77266c735848.23.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aafa3a21554cad9db0f4c3d71dcae8942a6b6c7a6aedc26f0c2c41f74efec74
|
| 3 |
+
size 34752
|