versae commited on
Commit
7b6df68
·
0 Parent(s):

Duplicate from modernisa/modernisa

Browse files
Files changed (4) hide show
  1. .gitattributes +27 -0
  2. README.md +39 -0
  3. app.py +58 -0
  4. requirements.txt +4 -0
.gitattributes ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.onnx filter=lfs diff=lfs merge=lfs -text
14
+ *.ot filter=lfs diff=lfs merge=lfs -text
15
+ *.parquet filter=lfs diff=lfs merge=lfs -text
16
+ *.pb filter=lfs diff=lfs merge=lfs -text
17
+ *.pt filter=lfs diff=lfs merge=lfs -text
18
+ *.pth filter=lfs diff=lfs merge=lfs -text
19
+ *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
22
+ *.tflite filter=lfs diff=lfs merge=lfs -text
23
+ *.tgz filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Modernisa Demo
3
+ emoji: 🖋️
4
+ colorFrom: green
5
+ colorTo: pink
6
+ sdk: gradio
7
+ app_file: app.py
8
+ pinned: false
9
+ duplicated_from: modernisa/modernisa
10
+ license: apache-2.0
11
+ ---
12
+
13
+ # Configuration
14
+
15
+ `title`: _string_
16
+ Display title for the Space
17
+
18
+ `emoji`: _string_
19
+ Space emoji (emoji-only character allowed)
20
+
21
+ `colorFrom`: _string_
22
+ Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
23
+
24
+ `colorTo`: _string_
25
+ Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
26
+
27
+ `sdk`: _string_
28
+ Can be either `gradio` or `streamlit`
29
+
30
+ `sdk_version` : _string_
31
+ Only applicable for `streamlit` SDK.
32
+ See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
33
+
34
+ `app_file`: _string_
35
+ Path to your main application file (which contains either `gradio` or `streamlit` Python code).
36
+ Path is relative to the root of the repository.
37
+
38
+ `pinned`: _boolean_
39
+ Whether the Space stays on top of your list.
app.py ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import random
2
+ import gradio as gr
3
+ from transformers import AutoTokenizer, pipeline, T5ForConditionalGeneration
4
+
5
+ model_name = "modernisa/modernisa-byt5-base" # "versae/byt5-base-finetuned-modernisa" # "versae/modernisa-pre"
6
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
7
+ model = T5ForConditionalGeneration.from_pretrained(model_name)
8
+
9
+ def modernisa(lines=None, file_obj=None):
10
+ is_file_valid = False
11
+ if file_obj:
12
+ is_file_valid = file_obj.name.endswith(".txt")
13
+ if is_file_valid:
14
+ with open(file_obj.name) as file:
15
+ lines = file.read()
16
+ generated_text = []
17
+ if lines:
18
+ lines = [line for line in lines.strip().split('\n') if line.strip()]
19
+ text2text_generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
20
+ outputs = []
21
+ for line in lines:
22
+ outputs += text2text_generator([line], max_length=150)
23
+ generated_text = [output["generated_text"] for output in outputs]
24
+ if is_file_valid and file_obj:
25
+ output_file = f"{file_obj.name.rsplit('.', 1)[0]}_modernized.txt"
26
+ else:
27
+ output_file = "modernized.txt"
28
+ with open(output_file, "w") as output:
29
+ output.write("\n".join(generated_text))
30
+ return "<br/>".join(generated_text), output_file
31
+
32
+
33
+ samples = [
34
+ """Otra vez, Don Iuan, me dad,
35
+ y otras mil vezes los braços.
36
+ Otra, y otras mil sean lazos
37
+ de nuestra antigua amistad.
38
+ Como venis?
39
+ Yo me siento
40
+ tan alegre, tan vfano,
41
+ tan venturoso, tan vano,
42
+ que no podrà el pensamiento
43
+ encareceros jamàs
44
+ las venturas que posseo,
45
+ porque el pensamiento creo"""
46
+ ]
47
+
48
+ gr.Interface(
49
+ fn=modernisa,
50
+ inputs=[
51
+ gr.inputs.Textbox(lines=12, label="Enter Spanish Golden Age text", default=random.choice(samples)),
52
+ gr.inputs.File(file_count="single", label="Or upload a plain text file (.txt)", type="file", optional=True),
53
+ ],
54
+ outputs=[
55
+ gr.outputs.HTML(label="Modern Spanish"),
56
+ gr.outputs.File(label="Download file"),
57
+ ]
58
+ ).launch(inline=False)
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ transformers
2
+ torch
3
+ gradio
4
+ streamlit