update readme
Browse files
README.md
CHANGED
|
@@ -39,11 +39,17 @@ This model represents a conventional T5 transformer in multitasking mode for tra
|
|
| 39 |
|
| 40 |
The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to <lang>:'. In this case, the source language may not be specified, in addition, the source text may be multilingual.
|
| 41 |
|
|
|
|
|
|
|
| 42 |
Fine tune from the base model: utrobinmv/t5_translate_en_ru_zh_large_1024
|
| 43 |
|
| 44 |
This version of the model was based on noisier data with a noise reduction function.
|
| 45 |
The model can additionally insert punctuation marks into sentences if they are missing from the source text. This is convenient to use for translating texts after ASR models.
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
Example translate Russian to Chinese
|
| 48 |
|
| 49 |
```python
|
|
|
|
| 39 |
|
| 40 |
The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to <lang>:'. In this case, the source language may not be specified, in addition, the source text may be multilingual.
|
| 41 |
|
| 42 |
+
|
| 43 |
+
|
| 44 |
Fine tune from the base model: utrobinmv/t5_translate_en_ru_zh_large_1024
|
| 45 |
|
| 46 |
This version of the model was based on noisier data with a noise reduction function.
|
| 47 |
The model can additionally insert punctuation marks into sentences if they are missing from the source text. This is convenient to use for translating texts after ASR models.
|
| 48 |
|
| 49 |
+
The model learned how to translate small markdown files while preserving the markup.
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
Example translate Russian to Chinese
|
| 54 |
|
| 55 |
```python
|