Update README.md
Browse files
README.md
CHANGED
|
@@ -97,25 +97,25 @@ Fine-tuned [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-r
|
|
| 97 |
|
| 98 |
## Usage
|
| 99 |
|
| 100 |
-
|
| 101 |
-
from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
|
| 102 |
|
| 103 |
-
|
| 104 |
-
|
| 105 |
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
tokens = nlp("အချစ်ဆိုတာလူတွေရှင်သန်ဖို့သဘာဝကပေးတဲ့လက်နက်လား၊ဒါမှမဟုတ်ယဉ်ကျေးမှုအရတီထွင်ထားတဲ့စိတ်ကူးယဉ်မှုသက်သက်လား။")
|
| 109 |
|
| 110 |
segmented_text = []
|
| 111 |
-
for
|
| 112 |
-
if
|
| 113 |
-
segmented_text.append(
|
| 114 |
else: # 'I' - append to previous word
|
| 115 |
-
segmented_text[-1] +=
|
| 116 |
segmented_text = " ".join(segmented_text)
|
| 117 |
|
| 118 |
-
|
|
|
|
|
|
|
| 119 |
```
|
| 120 |
|
| 121 |
## Label Mapping
|
|
|
|
| 97 |
|
| 98 |
## Usage
|
| 99 |
|
| 100 |
+
### Using Pipeline
|
|
|
|
| 101 |
|
| 102 |
+
```python
|
| 103 |
+
from transformers import pipeline
|
| 104 |
|
| 105 |
+
nlp = pipeline("token-classification", model="chuuhtetnaing/myanmar-text-segmentation-model", grouped_entities=True)
|
| 106 |
+
segments = nlp("အချစ်ဆိုတာလူတွေရှင်သန်ဖို့သဘာဝကပေးတဲ့လက်နက်လား၊ဒါမှမဟုတ်ယဉ်ကျေးမှုအရတီထွင်ထားတဲ့စိတ်ကူးယဉ်မှုသက်သက်လား။")
|
|
|
|
| 107 |
|
| 108 |
segmented_text = []
|
| 109 |
+
for segment in segments:
|
| 110 |
+
if segment["entity_group"] == "B":
|
| 111 |
+
segmented_text.append(segment["word"])
|
| 112 |
else: # 'I' - append to previous word
|
| 113 |
+
segmented_text[-1] += segment["word"]
|
| 114 |
segmented_text = " ".join(segmented_text)
|
| 115 |
|
| 116 |
+
print(segmented_text)
|
| 117 |
+
|
| 118 |
+
# အချစ်ဆိုတာ လူတွေရှင်သန်ဖို့ သဘာဝကပေးတဲ့လက်နက်လား၊ ဒါမှမဟုတ် ယဉ်ကျေးမှုအရ တီထွင်ထားတဲ့ စိတ်ကူးယဉ်မှုသက်သက်လား။
|
| 119 |
```
|
| 120 |
|
| 121 |
## Label Mapping
|