initial commit

app.py

@@ -1,7 +1,63 @@
+import spaces
 import gradio as gr
+from transformers import MT5ForConditionalGeneration, MT5Tokenizer,T5ForConditionalGeneration, T5Tokenizer
 
-def greet(name):
-    return "Hello " + name + "!!"
+models = {"finetuned mt5-base":"alakxender/mt5-base-dv-en", "madlad400-3b":"google/madlad400-3b-mt"}
+
+def tranlate(text:str,model_name:str):
+    if (len(text)>2000):
+        raise gr.Error(f"Try smaller text, yours is {len(text)}. try to fit to 2000 chars.")
+
+    if (model_name is None):
+        raise gr.Error("huh! not sure what to do without a model. select a model.")
+
+    if model_name =='finetuned mt5-base':
+        return mt5_translate(text,model_name)
+    else:
+        return t5_tranlaste(text,model_name)
+    
+@spaces.GPU(duration=120)
+def t5_tranlaste(text:str,model_name:str):
+
+    model = T5ForConditionalGeneration.from_pretrained(models[model_name], device_map="auto")
+    tokenizer = T5Tokenizer.from_pretrained(models[model_name])
+
+    text = f"<2en> {text}"
+    input_ids = tokenizer(text, return_tensors="pt").input_ids.to(model.device)
+    outputs = model.generate(input_ids=input_ids, max_new_tokens=1024*2)
+
+    translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    return translated_text
+
+def mt5_translate(text:str, model_name:str):
+    
+    model = MT5ForConditionalGeneration.from_pretrained(models[model_name])
+    tokenizer = MT5Tokenizer.from_pretrained(models[model_name])
+    inputs = tokenizer(text, return_tensors="pt")
+    result = model.generate(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'], max_new_tokens=1024*2)
+    translated_text = tokenizer.decode(result[0],  skip_special_tokens=True)
+    return translated_text
+
+css = """
+.textbox1 textarea {
+    font-size: 18px !important;
+    font-family: 'MV_Faseyha', 'Faruma', 'A_Faruma' !important;
+    line-height: 1.8 !important;
+}
+"""
+
+demo = gr.Interface(
+    fn=tranlate,
+    inputs= [
+        gr.Textbox(lines=5, label="Enter Dhivehi Text", rtl=True, elem_classes="textbox1"),
+        gr.Dropdown(choices=list(models.keys()), label="Select a model", value="finetuned mt5-base"),
+    ],
+    css=css,
+    outputs=gr.Textbox(label="English Translation"),
+    title="Dhivehi to English Translation",
+    description="Translate Dhivehi text to English",
+    examples=[["މާލޭގައި ފެންބޮޑުވާ މަގުތައް މަރާމާތު ކުރަން ފަށައިފި"]]
+)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()

gradio_cached_examples/16/indices.csv

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

gradio_cached_examples/16/log.csv

@@ -0,0 +1,2 @@
+English Translation,flag,username,timestamp
+flooding roads in the city,,,2024-06-20 17:50:47.570666

requirements.txt

@@ -0,0 +1,131 @@
+accelerate==0.31.0
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.2.0
+Authlib==1.3.1
+certifi==2024.6.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.0.4
+contourpy==1.2.1
+cryptography==42.0.8
+cycler==0.12.1
+datasets==2.19.2
+decorator==5.1.1
+dill==0.3.8
+dnspython==2.6.1
+email_validator==2.1.1
+exceptiongroup==1.2.1
+executing==2.0.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+ffmpy==0.3.2
+filelock==3.14.0
+fonttools==4.53.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+gradio==4.36.1
+gradio_client==1.0.1
+h11==0.14.0
+hf_transfer==0.1.6
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.3
+idna==3.7
+importlib_resources==6.4.0
+ipython==8.25.0
+itsdangerous==2.2.0
+jedi==0.19.1
+Jinja2==3.1.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.16
+networkx==3.3
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.5.40
+nvidia-nvtx-cu12==12.1.105
+orjson==3.10.3
+packaging==24.0
+pandas==2.2.2
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.3.0
+prompt_toolkit==3.0.47
+protobuf==3.20.3
+psutil==5.9.8
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==16.1.0
+pyarrow-hotfix==0.6
+pycparser==2.22
+pydantic==2.7.3
+pydantic_core==2.18.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+regex==2024.5.15
+requests==2.32.3
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.8
+safetensors==0.4.3
+semantic-version==2.10.0
+sentencepiece==0.2.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+spaces==0.28.3
+stack-data==0.6.3
+starlette==0.37.2
+sympy==1.12.1
+tokenizers==0.19.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.2.0
+tqdm==4.66.4
+traitlets==5.14.3
+transformers==4.41.2
+triton==2.2.0
+typer==0.12.3
+typing_extensions==4.12.1
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.1
+uvicorn==0.30.1
+uvloop==0.19.0
+watchfiles==0.22.0
+wcwidth==0.2.13
+websockets==11.0.3
+xxhash==3.4.1
+yarl==1.9.4