anzorq commited on
Commit
3e2e722
1 Parent(s): c0db4bc

add app.py

Browse files
Files changed (1) hide show
  1. app.py +26 -0
app.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+
3
+ from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
4
+
5
+ model_path = "anzorq/m2m100_418M_ft_ru-kbd_44K"
6
+ src_lang="ru"
7
+ tgt_lang="zu"
8
+
9
+ tokenizer = AutoTokenizer.from_pretrained(model_path, src_lang=src_lang)
10
+ model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
11
+
12
+ def translate(text):
13
+ inputs = tokenizer(text, return_tensors="pt")
14
+
15
+ translated_tokens = model.generate(
16
+ **inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang], num_beams=4, num_return_sequences=4
17
+ )
18
+
19
+ translations = []
20
+ for translation in tokenizer.batch_decode(translated_tokens, skip_special_tokens=True):
21
+ translations.append(translation)
22
+
23
+ return translations
24
+
25
+ iface = gr.Interface(fn=translate, inputs="text", outputs="text")
26
+ iface.launch()