Update README.md
Browse files
README.md
CHANGED
@@ -42,7 +42,7 @@ A metric that evaluates how similar the translated text is to the original text.
|
|
42 |
A method to evaluate translation accuracy based on how well character combinations match and the order of words. A drawback is that it might not be suitable for evaluating longer sentences.
|
43 |
|
44 |
### comet
|
45 |
-
|
46 |
A tool that uses machine learning models to automatically evaluate the quality of translations, although it is said to be similar to the evaluation ratings performed by humans. Because it is machine learning based, it has the weakness that the original model is highly dependent on the data used for training.
|
47 |
|
48 |
## vs. NLLB-200
|
@@ -135,7 +135,7 @@ However, performance is slightly reduced. Also, the ability to translate into la
|
|
135 |
[Sample Code For Free Colab webbigdata/ALMA-7B-Ja-V2-GPTQ-Ja-En](https://github.com/webbigdata-jp/python_sample/blob/master/ALMA_7B_Ja_V2_GPTQ_Ja_En_Free_Colab_sample.ipynb)
|
136 |
|
137 |
ファイル全体を一度に翻訳したい場合は、以下のColabをお試しください。
|
138 |
-
If you want to translate the entire file at once, try Colab below.
|
139 |
|
140 |
[ALMA_7B_Ja_GPTQ_Ja_En_batch_translation_sample](https://github.com/webbigdata-jp/python_sample/blob/master/ALMA_7B_Ja_V2_GPTQ_Ja_En_batch_translation_sample.ipynb)
|
141 |
|
@@ -158,4 +158,4 @@ Prevous Model [ALMA-7B-Ja](https://huggingface.co/webbigdata/ALMA-7B-Ja). (13.3
|
|
158 |
|
159 |
|
160 |
## about this work
|
161 |
-
- **This work was done by :** [webbigdata](https://webbigdata.jp/).
|
|
|
42 |
A method to evaluate translation accuracy based on how well character combinations match and the order of words. A drawback is that it might not be suitable for evaluating longer sentences.
|
43 |
|
44 |
### comet
|
45 |
+
機械学習モデルを使って翻訳の品質を自動的に評価するためのツール、人間の主観的評価に近いと言われていますが、機械学習ベースであるため、元々のモデルが学習に使ったデータに大きく依存するという弱点があります。
|
46 |
A tool that uses machine learning models to automatically evaluate the quality of translations, although it is said to be similar to the evaluation ratings performed by humans. Because it is machine learning based, it has the weakness that the original model is highly dependent on the data used for training.
|
47 |
|
48 |
## vs. NLLB-200
|
|
|
135 |
[Sample Code For Free Colab webbigdata/ALMA-7B-Ja-V2-GPTQ-Ja-En](https://github.com/webbigdata-jp/python_sample/blob/master/ALMA_7B_Ja_V2_GPTQ_Ja_En_Free_Colab_sample.ipynb)
|
136 |
|
137 |
ファイル全体を一度に翻訳したい場合は、以下のColabをお試しください。
|
138 |
+
If you want to translate the entire txt file at once, try Colab below.
|
139 |
|
140 |
[ALMA_7B_Ja_GPTQ_Ja_En_batch_translation_sample](https://github.com/webbigdata-jp/python_sample/blob/master/ALMA_7B_Ja_V2_GPTQ_Ja_En_batch_translation_sample.ipynb)
|
141 |
|
|
|
158 |
|
159 |
|
160 |
## about this work
|
161 |
+
- **This work was done by :** [webbigdata](https://webbigdata.jp/post-21151/).
|