Duplicate from deep-learning-analytics/GrammarCorrector

Co-authored-by: Priya Dwivedi <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+title: GrammarCorrector
+emoji: 📊
+colorFrom: red
+colorTo: gray
+sdk: streamlit
+app_file: app.py
+pinned: false
+duplicated_from: deep-learning-analytics/GrammarCorrector
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,34 @@
+import streamlit as st
+
+
+st.title("Correct Grammar with Transformers 🦄")
+st.write("")
+st.write("Input your text here!")
+
+default_value = "Mike and Anna is skiing"
+sent = st.text_area("Text", default_value, height = 50)
+num_return_sequences = st.sidebar.number_input('Number of Return Sequences', min_value=1, max_value=3, value=1, step=1)
+
+### Run Model
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+import torch
+torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
+tokenizer = T5Tokenizer.from_pretrained('deep-learning-analytics/GrammarCorrector')
+model = T5ForConditionalGeneration.from_pretrained('deep-learning-analytics/GrammarCorrector').to(torch_device)
+
+def correct_grammar(input_text,num_return_sequences=num_return_sequences):
+  batch = tokenizer([input_text],truncation=True,padding='max_length',max_length=64, return_tensors="pt").to(torch_device)
+  results = model.generate(**batch,max_length=64,num_beams=2, num_return_sequences=num_return_sequences, temperature=1.5)
+  #answer = tokenizer.batch_decode(results[0], skip_special_tokens=True)
+  return results
+  
+##Prompts
+results = correct_grammar(sent, num_return_sequences)
+
+generated_sequences = []
+for generated_sequence_idx, generated_sequence in enumerate(results):
+    # Decode text
+    text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True, skip_special_tokens=True)
+    generated_sequences.append(text)
+
+st.write(generated_sequences)

requirements.txt

@@ -0,0 +1,3 @@
+torch
+sentencepiece
+transformers