Duplicate from modernisa/modernisa

.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 +1,39 @@
+---
+title: Modernisa Demo
+emoji: 🖋️
+colorFrom: green
+colorTo: pink
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: modernisa/modernisa
+license: apache-2.0
+---
+
+# 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 +1,58 @@
+import random
+import gradio as gr
+from transformers import AutoTokenizer, pipeline, T5ForConditionalGeneration
+
+model_name = "modernisa/modernisa-byt5-base"  # "versae/byt5-base-finetuned-modernisa"  # "versae/modernisa-pre"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+
+def modernisa(lines=None, file_obj=None):
+    is_file_valid = False
+    if file_obj:
+        is_file_valid = file_obj.name.endswith(".txt")
+        if is_file_valid:
+            with open(file_obj.name) as file:
+                lines = file.read()
+    generated_text = []
+    if lines:
+        lines = [line for line in lines.strip().split('\n') if line.strip()]
+        text2text_generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+        outputs = []
+        for line in lines:
+            outputs += text2text_generator([line], max_length=150)
+        generated_text = [output["generated_text"] for output in outputs]
+        if is_file_valid and file_obj:
+            output_file = f"{file_obj.name.rsplit('.', 1)[0]}_modernized.txt"
+        else:
+            output_file = "modernized.txt"
+    with open(output_file, "w") as output:
+        output.write("\n".join(generated_text))
+    return "<br/>".join(generated_text), output_file
+
+
+samples = [
+"""Otra vez, Don Iuan, me dad,
+y otras mil vezes los braços.
+Otra, y otras mil sean lazos
+de nuestra antigua amistad.
+Como venis?
+Yo me siento
+tan alegre, tan vfano,
+tan venturoso, tan vano,
+que no podrà el pensamiento
+encareceros jamàs
+las venturas que posseo,
+porque el pensamiento creo"""
+]
+
+gr.Interface(
+    fn=modernisa,
+    inputs=[
+        gr.inputs.Textbox(lines=12, label="Enter Spanish Golden Age text", default=random.choice(samples)),
+        gr.inputs.File(file_count="single", label="Or upload a plain text file (.txt)", type="file", optional=True),
+    ],
+    outputs=[
+        gr.outputs.HTML(label="Modern Spanish"),
+        gr.outputs.File(label="Download file"),
+    ]
+).launch(inline=False)

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+gradio
+streamlit