update wer/cer with LM after 60 epochs
Browse files
README.md
CHANGED
|
@@ -22,7 +22,10 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Test WER
|
| 24 |
type: wer
|
| 25 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -35,8 +38,8 @@ It achieves the following results on the evaluation set:
|
|
| 35 |
- Training Loss: 0.268400
|
| 36 |
- Validation Loss: 0.088252
|
| 37 |
- WER without LM: 0.085588
|
| 38 |
-
- WER with LM: 0.
|
| 39 |
-
- CER with LM: 0.
|
| 40 |
|
| 41 |
|
| 42 |
## Model description
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Test WER
|
| 24 |
type: wer
|
| 25 |
+
value: 0.04440795062008041
|
| 26 |
+
- name: Test СER
|
| 27 |
+
type: сer
|
| 28 |
+
value: 0.010491234992390509
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 38 |
- Training Loss: 0.268400
|
| 39 |
- Validation Loss: 0.088252
|
| 40 |
- WER without LM: 0.085588
|
| 41 |
+
- WER with LM: 0.04440795062008041
|
| 42 |
+
- CER with LM: 0.010491234992390509
|
| 43 |
|
| 44 |
|
| 45 |
## Model description
|