Commit
·
da60070
1
Parent(s):
ca310ba
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,12 +5,8 @@ language:
|
|
| 5 |
- de
|
| 6 |
license: mit
|
| 7 |
widget:
|
| 8 |
-
- text: "ich glaub ich muss echt rewatchen like i [MASK] so empty was soll ich denn jetzt machen"
|
| 9 |
-
example_title: "Example 1"
|
| 10 |
- text: "I don't get [MASK] er damit erreichen will."
|
| 11 |
example_title: "Example 2"
|
| 12 |
-
- text: "Sagt ein(e) Head(in) [MASK] research! Researchen Sie mal ein bisschen mehr."
|
| 13 |
-
example_title: "Example 3"
|
| 14 |
---
|
| 15 |
|
| 16 |
# German-English Code-Switching BERT
|
|
@@ -18,7 +14,7 @@ widget:
|
|
| 18 |
A BERT-based model trained with masked language modelling on a large corpus of German--English code-switching. It was introduced in [this paper](). This model is case sensitive.
|
| 19 |
|
| 20 |
## Overview
|
| 21 |
-
- **
|
| 22 |
- **Training data:** The TongueSwitcher Corpus
|
| 23 |
- **Infrastructure**: 4x Nvidia A100 GPUs
|
| 24 |
- **Published**: 16 October 2023
|
|
@@ -27,6 +23,7 @@ A BERT-based model trained with masked language modelling on a large corpus of G
|
|
| 27 |
|
| 28 |
```
|
| 29 |
batch_size = 32
|
|
|
|
| 30 |
n_steps = 191,950
|
| 31 |
max_seq_len = 512
|
| 32 |
learning_rate = 1e-4
|
|
|
|
| 5 |
- de
|
| 6 |
license: mit
|
| 7 |
widget:
|
|
|
|
|
|
|
| 8 |
- text: "I don't get [MASK] er damit erreichen will."
|
| 9 |
example_title: "Example 2"
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# German-English Code-Switching BERT
|
|
|
|
| 14 |
A BERT-based model trained with masked language modelling on a large corpus of German--English code-switching. It was introduced in [this paper](). This model is case sensitive.
|
| 15 |
|
| 16 |
## Overview
|
| 17 |
+
- **Initialized language model:** bert-base-multilingual-cased
|
| 18 |
- **Training data:** The TongueSwitcher Corpus
|
| 19 |
- **Infrastructure**: 4x Nvidia A100 GPUs
|
| 20 |
- **Published**: 16 October 2023
|
|
|
|
| 23 |
|
| 24 |
```
|
| 25 |
batch_size = 32
|
| 26 |
+
epochs = 1
|
| 27 |
n_steps = 191,950
|
| 28 |
max_seq_len = 512
|
| 29 |
learning_rate = 1e-4
|