vrdn23 commited on
Commit
286d1cc
1 Parent(s): 53a3a16

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - g2p
7
  - cisco
8
  - Grapheme-to-Phoneme
 
9
  ---
10
 
11
  ## Model Summary
@@ -27,7 +28,7 @@ The model provides output in the form of phonemes along with their corresponding
27
  ```python
28
  from transformers import pipeline
29
 
30
- pipe = pipeline(task="translation", model="cisco-ai/mini-bart-g2p")
31
 
32
  text = "hello world"
33
  # DO NOT DO ```pipe(text)``` as this will produce unexpected results.
@@ -96,8 +97,7 @@ python run_translation.py \
96
  The model has some limitations in it's current form which we list for full transparency.
97
 
98
  - The `mini-bart-g2p` model is trained to only work on the English language.
99
- - The model does not produce consistent behavior when non-apostrophe punctuation symbols are part of the input word.
100
- - *We recommend stripping the words of all non-essential punctuation symbols before running it through the pipeline.*
101
  ```python
102
  text = "world world!"
103
  pipe(text.split())
 
6
  - g2p
7
  - cisco
8
  - Grapheme-to-Phoneme
9
+ pipeline_tag: text2text-generation
10
  ---
11
 
12
  ## Model Summary
 
28
  ```python
29
  from transformers import pipeline
30
 
31
+ pipe = pipeline(task="text2text-generation", model="cisco-ai/mini-bart-g2p")
32
 
33
  text = "hello world"
34
  # DO NOT DO ```pipe(text)``` as this will produce unexpected results.
 
97
  The model has some limitations in it's current form which we list for full transparency.
98
 
99
  - The `mini-bart-g2p` model is trained to only work on the English language.
100
+ - The model does not produce consistent behavior when non-apostrophe punctuation symbols are part of the input word. **We recommend stripping the words of all non-essential punctuation symbols before running it through the pipeline.**
 
101
  ```python
102
  text = "world world!"
103
  pipe(text.split())