Parsa Hosseini
commited on
Commit
•
d5aaf5d
1
Parent(s):
83e3f12
update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- superb
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-base-finetuned-ks
|
| 9 |
results: []
|
|
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# wav2vec2-base-finetuned-ks
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -44,6 +49,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
- num_epochs: 5
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.11.3
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- superb
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-base-finetuned-ks
|
| 11 |
results: []
|
|
|
|
| 17 |
# wav2vec2-base-finetuned-ks
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0894
|
| 22 |
+
- Accuracy: 0.9828
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 49 |
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
- num_epochs: 5
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:--------:|:---------------:|
|
| 56 |
+
| 0.5003 | 1.0 | 399 | 0.9643 | 0.4284 |
|
| 57 |
+
| 0.1868 | 2.0 | 798 | 0.9748 | 0.1628 |
|
| 58 |
+
| 0.1413 | 3.0 | 1197 | 0.9796 | 0.1128 |
|
| 59 |
+
| 0.0965 | 4.0 | 1596 | 0.0950 | 0.9826 |
|
| 60 |
+
| 0.0915 | 5.0 | 1995 | 0.0894 | 0.9828 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
### Framework versions
|
| 64 |
|
| 65 |
- Transformers 4.11.3
|