skytnt commited on
Commit
b43899d
1 Parent(s): 016b4b4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ The model is used to generate Japanese lyrics.
22
 
23
  ```python
24
  import torch
25
- from transformers import T5Tokenizer, GPT2LMHeadModel, TextGenerationPipeline
26
 
27
  tokenizer = T5Tokenizer.from_pretrained("skytnt/gpt2-japanese-lyric-small")
28
  model = GPT2LMHeadModel.from_pretrained("skytnt/gpt2-japanese-lyric-small")
@@ -64,5 +64,5 @@ print(gen_lyric("未来に揺れる花 過去にもあった花"))
64
 
65
  ## Training data
66
 
67
- Training data ([click to download](https://data.anyweb.xyz/dataset/lyric.zip)) contains 48,394 Japanese lyrics which are collected from [NetEasyMusic](https://music.163.com/) by [lyric_download](https://github.com/SkyTNT/lyric_downlowd)
68
 
 
22
 
23
  ```python
24
  import torch
25
+ from transformers import T5Tokenizer, GPT2LMHeadModel
26
 
27
  tokenizer = T5Tokenizer.from_pretrained("skytnt/gpt2-japanese-lyric-small")
28
  model = GPT2LMHeadModel.from_pretrained("skytnt/gpt2-japanese-lyric-small")
 
64
 
65
  ## Training data
66
 
67
+ [Training data](https://data.anyweb.xyz/dataset/lyric_clean.pkl) contains 143,587 Japanese lyrics which are collected from [uta-net](https://www.uta-net.com/) by [lyric_download](https://github.com/SkyTNT/lyric_downlowd)
68