Edit model card

This is the base model of zake7749/chinese-lyrics-generation-mass.

Example

from transformers import MT5ForConditionalGeneration, AutoTokenizer, Text2TextGenerationPipeline
model_name = "zake7749/text-to-lyric"
model = MT5ForConditionalGeneration.from_pretrained(model_tag)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# sentence to lyric.
text = "我吹過你吹過的晚風"
lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
print(f"Generated lyric: {lyric}")
# Generated lyric: 我吹過你吹過的晚風 你的溫柔讓我心醉神迷 你的笑容讓我心動不已 我們一起走過的時光 就像是陽光照耀著我們的夢 我們一起飛翔在藍天之上 在這片蒼穹下 你是我生命中最美好的風景

# keyword to lyric.
text = "青春 歌曲 歲月 黑夜"
lyric = pipe(template, max_length=128, top_p=0.8, do_sample=True, repetition_penalty=1.2)[0]['generated_text']
print(f"Generated lyric: {lyric}")
# Generated lyric: 唱著我青春的歌曲 歲月匆匆流轉 白天黑夜不停搖晃 想念你的笑容 陪伴著我的歌聲 歌聲在心中綻放 歲月無法阻擋
Downloads last month
3
Safetensors
Model size
582M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.