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: 29.
|
| 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 |
-
| 0.2295 | 1.13 | 3500 | 0.4268 |
|
| 57 |
-
| 0.179 | 1.29 | 4000 | 0.4088 |
|
| 58 |
-
| 0.161 | 1.45 | 4500 | 0.3923 |
|
| 59 |
-
| 0.1607 | 1.61 | 5000 | 0.3840 |
|
| 60 |
-
| 0.1336 | 1.77 | 5500 | 0.3783 |
|
| 61 |
-
| 0.1258 | 1.93 | 6000 | 0.3736 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 0.3658
|
| 24 |
+
- Cer: 29.0572
|
| 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: 3
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:-------:|:---------------:|
|
| 56 |
+
| 0.2295 | 1.13 | 3500 | 32.4577 | 0.4268 |
|
| 57 |
+
| 0.179 | 1.29 | 4000 | 32.1109 | 0.4088 |
|
| 58 |
+
| 0.161 | 1.45 | 4500 | 30.9241 | 0.3923 |
|
| 59 |
+
| 0.1607 | 1.61 | 5000 | 30.1640 | 0.3840 |
|
| 60 |
+
| 0.1336 | 1.77 | 5500 | 29.7573 | 0.3783 |
|
| 61 |
+
| 0.1258 | 1.93 | 6000 | 29.5906 | 0.3736 |
|
| 62 |
+
| 0.0725 | 2.09 | 6500 | 0.3842 | 30.3507 |
|
| 63 |
+
| 0.0692 | 2.25 | 7000 | 0.3776 | 30.0973 |
|
| 64 |
+
| 0.0635 | 2.41 | 7500 | 0.3740 | 29.5106 |
|
| 65 |
+
| 0.053 | 2.57 | 8000 | 0.3706 | 29.0772 |
|
| 66 |
+
| 0.0441 | 2.73 | 8500 | 0.3656 | 28.5238 |
|
| 67 |
+
| 0.0427 | 2.89 | 9000 | 0.3658 | 29.0572 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
runs/Mar16_11-24-32_4e9ad8212e20/events.out.tfevents.1710588301.4e9ad8212e20.27.0
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 sha256:0d6c46c9d50c18e1bbd0ae2b704950c83fa2a68a094018070cc8ca8430b3c450
|
| 3 |
+
size 35741
|