Update README.md

README.md

@@ -1,3 +1,68 @@
 ---
+language: ja
+tags:
+- ja
+- japanese
+- gpt2
+- text-generation
+- lm
+- nlp
 license: mit
+widget:
+- text: "未来に揺れる花 過去にもあった花"
 ---
+
+# Japanese GPT2 Lyric Model
+
+## Model description
+
+The model is used to generate Japanese lyrics.
+
+## How to use
+
+```python
+import torch
+from transformers import T5Tokenizer, GPT2LMHeadModel, TextGenerationPipeline
+
+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 = prompt_text.replace("\n", "[SEP]")
+    prompt_tokens = tokenizer.tokenize(prompt_text)
+    prompt_token_ids = tokenizer.convert_tokens_to_ids(prompt_tokens)
+    prompt_tensor = torch.LongTensor(prompt_token_ids)
+    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('[SEP]')]).replace(' ', '\u3000').replace(
+        '</s>', '\n\n---end---')
+    return generated_text
+
+
+print(gen_lyric("未来に揺れる花 過去にもあった花"))
+
+```
+
+## Training data
+
+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)
+