Update README.md
Browse files
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
tags:
|
3 |
- translation
|
4 |
- torch==1.8.0
|
|
|
|
|
5 |
---
|
6 |
### marianmt-zh_cn-th
|
7 |
* source languages: zh_cn
|
@@ -14,12 +16,14 @@ tags:
|
|
14 |
|
15 |
## Training
|
16 |
|
|
|
|
|
17 |
```
|
18 |
export WANDB_PROJECT=marianmt-zh_cn-th
|
19 |
-
python train_model.py --input_fname ../data/v1/Train.csv
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
```
|
24 |
|
25 |
## Usage
|
|
|
2 |
tags:
|
3 |
- translation
|
4 |
- torch==1.8.0
|
5 |
+
widget:
|
6 |
+
- text: "Inference Unavailable"
|
7 |
---
|
8 |
### marianmt-zh_cn-th
|
9 |
* source languages: zh_cn
|
|
|
16 |
|
17 |
## Training
|
18 |
|
19 |
+
Training scripts from [LalitaDeelert/NLP-ZH_TH-Project](https://github.com/LalitaDeelert/NLP-ZH_TH-Project). Experiments tracked at [cstorm125/marianmt-zh_cn-th](https://wandb.ai/cstorm125/marianmt-zh_cn-th).
|
20 |
+
|
21 |
```
|
22 |
export WANDB_PROJECT=marianmt-zh_cn-th
|
23 |
+
python train_model.py --input_fname ../data/v1/Train.csv \\
|
24 |
+
\t--output_dir ../models/marianmt-zh_cn-th \\
|
25 |
+
\t--source_lang zh --target_lang th \\
|
26 |
+
\t--metric_tokenize th_syllable --fp16 --batch_size 64
|
27 |
```
|
28 |
|
29 |
## Usage
|