Duplicate from VuAI/VuAI-vi2vi_vn98

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: VuAI-vi2vi Vn98
+emoji: 🔥
+colorFrom: indigo
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: VuAI/VuAI-vi2vi_vn98
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+import os, time, re
+import gradio as gr
+
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+def inference(input_sentence, name_model):
+    # Load model
+    access_token = os.getenv("access_token")
+    tokenizer = AutoTokenizer.from_pretrained(name_model, use_auth_token=access_token)
+    model = AutoModelForSeq2SeqLM.from_pretrained(name_model, use_auth_token=access_token)
+    #tokenizer = AutoTokenizer.from_pretrained(name_model )
+    # model = AutoModelForSeq2SeqLM.from_pretrained(name_model)
+
+    # Load input and encode
+    input_ids = tokenizer.encode(input_sentence, return_tensors="pt")
+
+    # Generate translation
+    translation = model.generate(input_ids=input_ids, max_length = 512)[0]
+
+    # Decode the generated translation
+    translated_text = tokenizer.decode(translation, skip_special_tokens=True)
+
+    return translated_text.replace('▁', ' ')
+
+def translator(input_sentence, name_model):
+    # name_model = "model"
+    name_model = 'VuAI/vi2vi_vn98'
+    start_time = time.time()
+
+    input_sentence = input_sentence.replace('【', '[').replace('】', ']').replace('“', '"').replace('”', '"').replace('." ', '."\n').replace('?" ', '?"\n').replace('!" ', '!"\n').replace(': "', ':\n"').replace(', "', ':\n"')
+    input_sentence = input_sentence.split('\n')
+    
+    result = ''
+    percent_complete = 0
+    for i in input_sentence:
+        if i != '' and i != ' ':
+            if i.find('"') == 0 and i.find('"',1) == (len(i)-1):
+                str_out = '"' + inference(i.replace('"',''), name_model) + '"'
+            elif i.find('[') == 0:
+                str_out = '[' + inference(i.replace('[','').replace(']',''), name_model) + ']'
+            else:
+                str_out = inference(i, name_model)
+            # st.sidebar.write(str_out)
+            result += str_out + '\n'
+            
+        percent_complete += 1/len(input_sentence)
+
+    title_str = re.findall('^Chương\s\d+:\s.*\n', result)
+    if title_str:
+        result = result.replace(title_str[0], title_str[0].title())
+    
+    end_time = time.time()
+    process_time = end_time - start_time
+    # status_bar.success('Đã dịch thành công! \n\tThời gian dịch: ' + str(process_time) + ' giây', icon="✅")
+    
+    return result
+
+def login(username, password):
+    if username == os.getenv("username") and password == os.getenv("password"):
+        return True
+
+if __name__ == "__main__":
+    path = "./model/"
+    
+    # name_model = st.selectbox(
+    #     'Select Model?',
+    #     ['VuAI/vi2vi_vn98']
+    # )
+    MODELS = ['VuAI/vi2vi_vn98']
+    gr.Interface(fn=translator, 
+                inputs=[
+                    gr.inputs.Textbox(lines=5, label="Input Text"),
+                    gr.components.Dropdown(label="Select Model?", choices=MODELS, value="VuAI/vi2vi_vn98"),
+                ],
+                outputs=gr.inputs.Textbox(label="Result"),
+                title="Translation Demo"
+                ).launch(auth=login)

model/demo.txt

@@ -0,0 +1 @@
+demo

nlp.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59dc75a02ec3d4d03a68762d768a58fc69fd8506acc5234a5fc38bfb715b5401
+size 1100604445

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+torch