Commit
•
b11d440
1
Parent(s):
436e39b
Librarian Bot: Add base_model information to model (#2)
Browse files- Librarian Bot: Add base_model information to model (97cabd5e242da7d395a41f72771d2fa4f839f05b)
Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,7 +1,5 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
- en
|
4 |
-
license:
|
5 |
- cc-by-nc-sa-4.0
|
6 |
- apache-2.0
|
7 |
tags:
|
@@ -11,32 +9,46 @@ tags:
|
|
11 |
- error-correction
|
12 |
- grammar synthesis
|
13 |
- FLAN
|
14 |
-
|
15 |
datasets:
|
16 |
- jfleg
|
|
|
|
|
17 |
widget:
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
example_title:
|
31 |
-
- text:
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
example_title:
|
37 |
-
- text:
|
38 |
-
|
39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
inference:
|
41 |
parameters:
|
42 |
max_length: 96
|
@@ -44,7 +56,8 @@ inference:
|
|
44 |
num_beams: 2
|
45 |
repetition_penalty: 1.15
|
46 |
length_penalty: 1
|
47 |
-
early_stopping:
|
|
|
48 |
---
|
49 |
|
50 |
# grammar-synthesis: flan-t5-xl
|
|
|
1 |
---
|
2 |
+
license:
|
|
|
|
|
3 |
- cc-by-nc-sa-4.0
|
4 |
- apache-2.0
|
5 |
tags:
|
|
|
9 |
- error-correction
|
10 |
- grammar synthesis
|
11 |
- FLAN
|
|
|
12 |
datasets:
|
13 |
- jfleg
|
14 |
+
languages:
|
15 |
+
- en
|
16 |
widget:
|
17 |
+
- text: There car broke down so their hitching a ride to they're class.
|
18 |
+
example_title: compound-1
|
19 |
+
- text: i can has cheezburger
|
20 |
+
example_title: cheezburger
|
21 |
+
- text: so em if we have an now so with fito ringina know how to estimate the tren
|
22 |
+
given the ereafte mylite trend we can also em an estimate is nod s i again tort
|
23 |
+
watfettering an we have estimated the trend an called wot to be called sthat of
|
24 |
+
exty right now we can and look at wy this should not hare a trend i becan we just
|
25 |
+
remove the trend an and we can we now estimate tesees ona effect of them exty
|
26 |
+
example_title: Transcribed Audio Example 2
|
27 |
+
- text: My coworker said he used a financial planner to help choose his stocks so
|
28 |
+
he wouldn't loose money.
|
29 |
+
example_title: incorrect word choice (context)
|
30 |
+
- text: good so hve on an tadley i'm not able to make it to the exla session on monday
|
31 |
+
this week e which is why i am e recording pre recording an this excelleision and
|
32 |
+
so to day i want e to talk about two things and first of all em i wont em wene
|
33 |
+
give a summary er about ta ohow to remove trents in these nalitives from time
|
34 |
+
series
|
35 |
+
example_title: lowercased audio transcription output
|
36 |
+
- text: Frustrated, the chairs took me forever to set up.
|
37 |
+
example_title: dangling modifier
|
38 |
+
- text: I would like a peice of pie.
|
39 |
+
example_title: simple miss-spelling
|
40 |
+
- text: Which part of Zurich was you going to go hiking in when we were there for
|
41 |
+
the first time together? ! ?
|
42 |
+
example_title: chatbot on Zurich
|
43 |
+
- text: Most of the course is about semantic or content of language but there are
|
44 |
+
also interesting topics to be learned from the servicefeatures except statistics
|
45 |
+
in characters in documents. At this point, Elvthos introduces himself as his native
|
46 |
+
English speaker and goes on to say that if you continue to work on social scnce,
|
47 |
+
example_title: social science ASR summary output
|
48 |
+
- text: they are somewhat nearby right yes please i'm not sure how the innish is tepen
|
49 |
+
thut mayyouselect one that istatte lo variants in their property e ere interested
|
50 |
+
and anyone basical e may be applyind reaching the browing approach were
|
51 |
+
- example_title: medical course audio transcription
|
52 |
inference:
|
53 |
parameters:
|
54 |
max_length: 96
|
|
|
56 |
num_beams: 2
|
57 |
repetition_penalty: 1.15
|
58 |
length_penalty: 1
|
59 |
+
early_stopping: true
|
60 |
+
base_model: google/flan-t5-xl
|
61 |
---
|
62 |
|
63 |
# grammar-synthesis: flan-t5-xl
|