pszemraj commited on
Commit
9249e22
1 Parent(s): 44d3754

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -5
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  license:
3
  - cc-by-nc-sa-4.0
4
  - apache-2.0
@@ -8,14 +10,16 @@ tags:
8
  - punctuation
9
  - error-correction
10
  - grammar synthesis
 
11
 
12
  datasets:
13
  - jfleg
14
  widget:
15
- - text: "i can has cheezburger"
16
- example_title: "cheezburger"
17
  - text: "There car broke down so their hitching a ride to they're class."
18
  example_title: "compound-1"
 
 
19
  - text: "so em if we have an now so with fito ringina know how to estimate the tren given the ereafte mylite trend we can also em an estimate is nod s
20
  i again tort watfettering an we have estimated the trend an
21
  called wot to be called sthat of exty right now we can and look at
@@ -28,17 +32,26 @@ tesees ona effect of them exty"
28
  an this excelleision and so to day i want e to talk about two things and first of all em i wont em wene give a summary er about
29
  ta ohow to remove trents in these nalitives from time series"
30
  example_title: "lowercased audio transcription output"
 
 
 
 
 
 
 
 
 
 
31
 
32
  parameters:
33
  max_length: 128
34
- min_length: 2
35
  num_beams: 8
36
- repetition_penalty: 1.3
37
  length_penalty: 1
38
  early_stopping: True
39
  ---
40
 
41
-
42
  # grammar-synthesis-small (beta)
43
 
44
  This model is a fine-tuned version of [google/t5-small-lm-adapt](https://huggingface.co/google/t5-small-lm-adapt) for grammar correction on an expanded version of the [JFLEG](https://paperswithcode.com/dataset/jfleg) dataset.
 
1
  ---
2
+ languages:
3
+ - en
4
  license:
5
  - cc-by-nc-sa-4.0
6
  - apache-2.0
 
10
  - punctuation
11
  - error-correction
12
  - grammar synthesis
13
+ - FLAN
14
 
15
  datasets:
16
  - jfleg
17
  widget:
18
+
 
19
  - text: "There car broke down so their hitching a ride to they're class."
20
  example_title: "compound-1"
21
+ - text: "i can has cheezburger"
22
+ example_title: "cheezburger"
23
  - text: "so em if we have an now so with fito ringina know how to estimate the tren given the ereafte mylite trend we can also em an estimate is nod s
24
  i again tort watfettering an we have estimated the trend an
25
  called wot to be called sthat of exty right now we can and look at
 
32
  an this excelleision and so to day i want e to talk about two things and first of all em i wont em wene give a summary er about
33
  ta ohow to remove trents in these nalitives from time series"
34
  example_title: "lowercased audio transcription output"
35
+ - text: "Frustrated, the chairs took me forever to set up."
36
+ example_title: "dangling modifier"
37
+ - text: "I would like a peice of pie."
38
+ example_title: "miss-spelling"
39
+ - text: "Which part of Zurich was you going to go hiking in when we were there for the first time together? ! ?"
40
+ example_title: "chatbot on Zurich"
41
+ - text: "Most of the course is about semantic or content of language but there are also interesting topics to be learned from the servicefeatures except statistics in characters in documents. At this point, Elvthos introduces himself as his native English speaker and goes on to say that if you continue to work on social scnce,"
42
+ example_title: "social science ASR summary output"
43
+ - text: "they are somewhat nearby right yes please i'm not sure how the innish is tepen thut mayyouselect one that istatte lo variants in their property e ere interested and anyone basical e may be applyind reaching the browing approach were"
44
+ - "medical course audio transcription"
45
 
46
  parameters:
47
  max_length: 128
48
+ min_length: 4
49
  num_beams: 8
50
+ repetition_penalty: 1.21
51
  length_penalty: 1
52
  early_stopping: True
53
  ---
54
 
 
55
  # grammar-synthesis-small (beta)
56
 
57
  This model is a fine-tuned version of [google/t5-small-lm-adapt](https://huggingface.co/google/t5-small-lm-adapt) for grammar correction on an expanded version of the [JFLEG](https://paperswithcode.com/dataset/jfleg) dataset.