update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# wav2vec2-xlsr-53-espeak-cv-ft-evn5-ntsema-colab
|
31 |
|
32 |
-
This model is a fine-tuned version of [
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Wer: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -51,7 +51,7 @@ More information needed
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
-
- learning_rate: 0.
|
55 |
- train_batch_size: 4
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
@@ -67,10 +67,8 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
-
|
|
71 |
-
| 0.
|
72 |
-
| 0.1926 | 18.46 | 1200 | 2.2109 | 0.99 |
|
73 |
-
| 0.121 | 24.61 | 1600 | 2.3655 | 0.9867 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
+
value: 0.9833333333333333
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# wav2vec2-xlsr-53-espeak-cv-ft-evn5-ntsema-colab
|
31 |
|
32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xlsr-53-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-xlsr-53-espeak-cv-ft) on the audiofolder dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.9757
|
35 |
+
- Wer: 0.9833
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0005
|
55 |
- train_batch_size: 4
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 5.7869 | 11.11 | 400 | 1.5999 | 0.9967 |
|
71 |
+
| 0.7026 | 22.22 | 800 | 1.9757 | 0.9833 |
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|