Commit
•
a7d6aa1
1
Parent(s):
ac0dd7f
update model card README.md
Browse files
README.md
CHANGED
@@ -13,13 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [crossdelenna/wav2vec2-large-en-in-lm](https://huggingface.co/crossdelenna/wav2vec2-large-en-in-lm) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
-
|
17 |
-
-
|
18 |
-
- eval_runtime: 21.8548
|
19 |
-
- eval_samples_per_second: 7.55
|
20 |
-
- eval_steps_per_second: 0.961
|
21 |
-
- epoch: 10.0
|
22 |
-
- step: 1210
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -48,6 +43,15 @@ The following hyperparameters were used during training:
|
|
48 |
- num_epochs: 30
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
### Framework versions
|
52 |
|
53 |
- Transformers 4.17.0
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [crossdelenna/wav2vec2-large-en-in-lm](https://huggingface.co/crossdelenna/wav2vec2-large-en-in-lm) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.0478
|
17 |
+
- Wer: 0.0951
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
43 |
- num_epochs: 30
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
50 |
+
| 0.1589 | 10.0 | 1210 | 0.0754 | 0.1088 |
|
51 |
+
| 0.1369 | 20.0 | 2420 | 0.0527 | 0.0991 |
|
52 |
+
| 0.1208 | 30.0 | 3630 | 0.0478 | 0.0951 |
|
53 |
+
|
54 |
+
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.17.0
|