mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-24 23:08:57 +06:00
added model_card for model codeswitch-hineng-lid-lince and codeswitch-spaeng-lid-lince (#6663)
* Create README.md * Update README.md * Create README.md * Update README.md
This commit is contained in:
parent
97bb2497ab
commit
068df740bd
@ -0,0 +1,37 @@
|
||||
---
|
||||
language:
|
||||
- hi
|
||||
- en
|
||||
---
|
||||
|
||||
# codeswitch-hineng-lid-lince
|
||||
This is a pretrained model for **language identification** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home)
|
||||
|
||||
## Identify Language
|
||||
|
||||
* Method-1
|
||||
|
||||
```py
|
||||
|
||||
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
|
||||
|
||||
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
|
||||
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)
|
||||
|
||||
lid_model("put any hindi english code-mixed sentence")
|
||||
|
||||
```
|
||||
|
||||
* Method-2
|
||||
|
||||
```py
|
||||
# !pip install codeswitch
|
||||
from codeswitch.codeswitch import LanguageIdentification
|
||||
lid = LanguageIdentification('hin-eng')
|
||||
text = "" # your code-mixed sentence
|
||||
result = lid.identify(text)
|
||||
print(result)
|
||||
```
|
||||
|
@ -0,0 +1,36 @@
|
||||
---
|
||||
language:
|
||||
- es
|
||||
- en
|
||||
---
|
||||
|
||||
# codeswitch-spaeng-lid-lince
|
||||
This is a pretrained model for **language identification** of `spanish-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home)
|
||||
|
||||
## Identify Language
|
||||
|
||||
* Method-1
|
||||
|
||||
```py
|
||||
|
||||
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-spaeng-lid-lince")
|
||||
|
||||
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-spaeng-lid-lince")
|
||||
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)
|
||||
|
||||
lid_model("put any spanish english code-mixed sentence")
|
||||
|
||||
```
|
||||
|
||||
* Method-2
|
||||
|
||||
```py
|
||||
# !pip install codeswitch
|
||||
from codeswitch.codeswitch import LanguageIdentification
|
||||
lid = LanguageIdentification('spa-eng')
|
||||
text = "" # your code-mixed sentence
|
||||
result = lid.identify(text)
|
||||
print(result)
|
||||
```
|
Loading…
Reference in New Issue
Block a user