Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,23 @@ This modelcard aims to be a base template for new models. It has been generated
|
|
| 41 |
## Uses
|
| 42 |
|
| 43 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
|
|
|
|
|
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Direct Use
|
| 46 |
|
| 47 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
|
@@ -155,6 +171,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 155 |
- **Compute Region:** [More Information Needed]
|
| 156 |
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
|
|
|
|
| 158 |
## Technical Specifications [optional]
|
| 159 |
|
| 160 |
### Model Architecture and Objective
|
|
|
|
| 41 |
## Uses
|
| 42 |
|
| 43 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
import ctranslate2
|
| 45 |
+
import transformers
|
| 46 |
|
| 47 |
+
translator = ctranslate2.Translator("t5_ct2")
|
| 48 |
+
tokenizer = transformers.AutoTokenizer.from_pretrained("t5_ct2")
|
| 49 |
+
|
| 50 |
+
input_text = " translate German to English: Ich erkläre die am Freitag, dem 17. Dezember 1999 unterbrochene Sitzungsperiode des Europäischen Parlaments für wieder aufgenommen, und wünsche Ihnen nochmals ein glückliches neues Jahr in der Hoffnung, daß Sie eine angenehme Festzeit genossen haben. Obwohl der gefürchtete 'Jahrtausendfehler' nicht zustande gekommen ist, erlitten die Menschen in einigen Ländern noch immer eine Reihe von Naturkatastrophen, die wirklich furchtbar waren."
|
| 51 |
+
input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(input_text))
|
| 52 |
+
|
| 53 |
+
results = translator.translate_batch([input_tokens])
|
| 54 |
+
|
| 55 |
+
output_tokens = results[0].hypotheses[0]
|
| 56 |
+
output_text = tokenizer.decode(tokenizer.convert_tokens_to_ids(output_tokens))
|
| 57 |
+
|
| 58 |
+
print(output_text)
|
| 59 |
+
|
| 60 |
+
If u want to translate en to de , you can change the prefix " translate English to German" is ok.
|
| 61 |
### Direct Use
|
| 62 |
|
| 63 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
|
|
|
| 171 |
- **Compute Region:** [More Information Needed]
|
| 172 |
- **Carbon Emitted:** [More Information Needed]
|
| 173 |
|
| 174 |
+
|
| 175 |
## Technical Specifications [optional]
|
| 176 |
|
| 177 |
### Model Architecture and Objective
|