File size: 2,021 Bytes
b6d59f3 b677d18 b6d59f3 b677d18 bd8bd0b b6d59f3 b677d18 216aa42 b677d18 b43899d b677d18 72268b6 b677d18 e47df31 b677d18 e47df31 b677d18 bd8bd0b b677d18 1eb9075 b677d18 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
---
language: ja
tags:
- ja
- japanese
- gpt2
- text-generation
- lm
- nlp
license: mit
widget:
- text: "桜が咲く"
---
# Japanese GPT2 Lyric Model
## Model description
The model is used to generate Japanese lyrics.
You can try it on my website [https://lyric.fab.moe/](https://lyric.fab.moe/#/)
## How to use
```python
import torch
from transformers import T5Tokenizer, GPT2LMHeadModel
tokenizer = T5Tokenizer.from_pretrained("skytnt/gpt2-japanese-lyric-small")
model = GPT2LMHeadModel.from_pretrained("skytnt/gpt2-japanese-lyric-small")
def gen_lyric(prompt_text: str):
prompt_text = "<s>" + prompt_text.replace("\n", "\\n ")
prompt_tokens = tokenizer.tokenize(prompt_text)
prompt_token_ids = tokenizer.convert_tokens_to_ids(prompt_tokens)
prompt_tensor = torch.LongTensor(prompt_token_ids).to(device)
prompt_tensor = prompt_tensor.view(1, -1)
# model forward
output_sequences = model.generate(
input_ids=prompt_tensor,
max_length=512,
top_p=0.95,
top_k=40,
temperature=1.0,
do_sample=True,
early_stopping=True,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
num_return_sequences=1
)
# convert model outputs to readable sentence
generated_sequence = output_sequences.tolist()[0]
generated_tokens = tokenizer.convert_ids_to_tokens(generated_sequence)
generated_text = tokenizer.convert_tokens_to_string(generated_tokens)
generated_text = "\n".join([s.strip() for s in generated_text.split('\\n')]).replace(' ', '\u3000').replace('<s>', '').replace('</s>', '\n\n---end---')
return generated_text
print(gen_lyric("桜が咲く"))
```
## Training data
[Training data](https://github.com/SkyTNT/gpt2-japanese-lyric/raw/main/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)
|