dpc commited on
Commit
caccbf7
·
1 Parent(s): ca29cd4
Files changed (3) hide show
  1. README.md +4 -4
  2. app.py +32 -0
  3. requirements.txt +3 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- title: Vien
3
- emoji: 🏢
4
- colorFrom: purple
5
- colorTo: blue
6
  sdk: gradio
7
  app_file: app.py
8
  pinned: false
 
1
  ---
2
+ title: Vietnamese - English Translation
3
+ emoji: 🐠
4
+ colorFrom: yellow
5
+ colorTo: gray
6
  sdk: gradio
7
  app_file: app.py
8
  pinned: false
app.py ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Based on example code of https://huggingface.co/facebook/m2m100_1.2B
2
+
3
+
4
+ import gradio as gr
5
+ from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
6
+ model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_1.2B")
7
+ tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_1.2B")
8
+
9
+ # from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
10
+ # tokenizer = AutoTokenizer.from_pretrained("facebook/m2m100_1.2B")
11
+ # model = AutoModelForSeq2SeqLM.from_pretrained("facebook/m2m100_1.2B")
12
+
13
+
14
+ def vi_en(Vietnamese_Text):
15
+ tokenizer.src_lang = "vi"
16
+ encoded_vi = tokenizer(Vietnamese_Text, return_tensors="pt")
17
+ generated_tokens = model.generate(
18
+ **encoded_vi, forced_bos_token_id=tokenizer.get_lang_id("en"))
19
+ res = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
20
+ return res
21
+ # if res:
22
+ # return '\n'.join(res)
23
+
24
+
25
+ iface = gr.Interface(
26
+ fn=vi_en,
27
+ title="Vietnamese to English",
28
+ description="Using/testing facebook/m2m100_1.2B pre-trained model",
29
+ inputs=gr.inputs.Textbox(lines=5, placeholder="Enter text in Vietnamese"),
30
+ outputs="text")
31
+
32
+ iface.launch()
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ torch
2
+ sentencepiece
3
+ transformers