Spaces:
Running
on
Zero
Running
on
Zero
| import gradio as gr | |
| from openai import OpenAI | |
| import requests | |
| import json | |
| # from volcenginesdkarkruntime import Ark | |
| import torch | |
| import torchaudio | |
| from einops import rearrange | |
| import argparse | |
| import json | |
| import os | |
| import spaces | |
| from tqdm import tqdm | |
| import random | |
| import numpy as np | |
| import sys | |
| import base64 | |
| from diffrhythm.infer.infer_utils import ( | |
| get_reference_latent, | |
| get_lrc_token, | |
| get_audio_style_prompt, | |
| get_text_style_prompt, | |
| prepare_model, | |
| get_negative_style_prompt | |
| ) | |
| from diffrhythm.infer.infer import inference | |
| MAX_SEED = np.iinfo(np.int32).max | |
| device='cuda' | |
| cfm, tokenizer, muq, vae, eval_model, eval_muq = prepare_model(max_frames=6144, device=device) | |
| cfm = torch.compile(cfm) | |
| def infer_music(lrc, ref_audio_path, text_prompt, current_prompt_type, seed=42, | |
| randomize_seed=False, steps=32, cfg_strength=4.0, file_type='wav', | |
| odeint_method='euler', preference_infer="quality first", Music_Duration=285, edit=False, | |
| edit_segments=None, device='cuda'): | |
| max_frames = 2048 if Music_Duration == 95 else 6144 | |
| sway_sampling_coef = -1 if steps < 32 else None | |
| if randomize_seed: | |
| seed = random.randint(0, MAX_SEED) | |
| torch.manual_seed(seed) | |
| vocal_flag = False | |
| try: | |
| lrc_prompt, start_time, end_frame, song_duration = get_lrc_token(max_frames, lrc, tokenizer, Music_Duration, device) | |
| if current_prompt_type == 'audio': | |
| style_prompt, vocal_flag = get_audio_style_prompt(muq, ref_audio_path) | |
| else: | |
| style_prompt = get_text_style_prompt(muq, text_prompt) | |
| except Exception as e: | |
| raise gr.Error(f"Error: {str(e)}") | |
| negative_style_prompt = get_negative_style_prompt(device) | |
| latent_prompt, pred_frames = get_reference_latent(device, max_frames, edit, edit_segments, ref_audio_path, vae) | |
| if preference_infer == "quality first": | |
| batch_infer_num = 5 | |
| else: | |
| batch_infer_num = 1 | |
| generated_song = inference(cfm_model=cfm, | |
| vae_model=vae, | |
| eval_model=eval_model, | |
| eval_muq=eval_muq, | |
| cond=latent_prompt, | |
| text=lrc_prompt, | |
| duration=end_frame, | |
| style_prompt=style_prompt, | |
| negative_style_prompt=negative_style_prompt, | |
| steps=steps, | |
| cfg_strength=cfg_strength, | |
| sway_sampling_coef=sway_sampling_coef, | |
| start_time=start_time, | |
| file_type=file_type, | |
| vocal_flag=vocal_flag, | |
| odeint_method=odeint_method, | |
| pred_frames=pred_frames, | |
| batch_infer_num=batch_infer_num, | |
| song_duration=song_duration | |
| ) | |
| return generated_song | |
| def R1_infer1(theme, tags_gen, language): | |
| try: | |
| client = OpenAI(api_key=os.getenv('HS_DP_API'), base_url = "https://ark.cn-beijing.volces.com/api/v3") | |
| llm_prompt = """ | |
| 请围绕"{theme}"主题生成一首符合"{tags}"风格的语言为{language}的完整歌词。严格遵循以下要求： | |
| ### **强制格式规则** | |
| 1. **仅输出时间戳和歌词**，禁止任何括号、旁白、段落标记（如副歌、间奏、尾奏等注释）。 | |
| 2. 每行格式必须为 `[mm:ss.xx]歌词内容`，时间戳与歌词间无空格，歌词内容需完整连贯。 | |
| 3. 时间戳需自然分布，**第一句歌词起始时间不得为 [00:00.00]**，需考虑前奏空白。 | |
| ### **内容与结构要求** | |
| 1. 歌词应富有变化，使情绪递进，整体连贯有层次感。**每行歌词长度应自然变化**，切勿长度一致，导致很格式化。 | |
| 2. **时间戳分配应根据歌曲的标签、歌词的情感、节奏来合理推测**，而非机械地按照歌词长度分配。 | |
| 3. 间奏/尾奏仅通过时间空白体现（如从 [02:30.00] 直接跳至 [02:50.00]），**无需文字描述**。 | |
| ### **负面示例（禁止出现）** | |
| - 错误：[01:30.00](钢琴间奏) | |
| - 错误：[02:00.00][副歌] | |
| - 错误：空行、换行符、注释 | |
| """ | |
| response = client.chat.completions.create( | |
| model="ep-20250304144033-nr9wl", | |
| messages=[ | |
| {"role": "system", "content": "You are a professional musician who has been invited to make music-related comments."}, | |
| {"role": "user", "content": llm_prompt.format(theme=theme, tags=tags_gen, language=language)}, | |
| ], | |
| stream=False | |
| ) | |
| info = response.choices[0].message.content | |
| return info | |
| except requests.exceptions.RequestException as e: | |
| print(f'请求出错: {e}') | |
| return {} | |
| def R1_infer2(tags_lyrics, lyrics_input): | |
| client = OpenAI(api_key=os.getenv('HS_DP_API'), base_url = "https://ark.cn-beijing.volces.com/api/v3") | |
| llm_prompt = """ | |
| {lyrics_input}这是一首歌的歌词,每一行是一句歌词,{tags_lyrics}是我希望这首歌的风格，我现在想要给这首歌的每一句歌词打时间戳得到LRC，我希望时间戳分配应根据歌曲的标签、歌词的情感、节奏来合理推测，而非机械地按照歌词长度分配。第一句歌词的时间戳应考虑前奏长度，避免歌词从 `[00:00.00]` 直接开始。严格按照 LRC 格式输出歌词，每行格式为 `[mm:ss.xx]歌词内容`。最后的结果只输出LRC,不需要其他的解释。 | |
| """ | |
| response = client.chat.completions.create( | |
| model="ep-20250304144033-nr9wl", | |
| messages=[ | |
| {"role": "system", "content": "You are a professional musician who has been invited to make music-related comments."}, | |
| {"role": "user", "content": llm_prompt.format(lyrics_input=lyrics_input, tags_lyrics=tags_lyrics)}, | |
| ], | |
| stream=False | |
| ) | |
| info = response.choices[0].message.content | |
| return info | |
| css = """ | |
| /* 固定文本域高度并强制滚动条 */ | |
| .lyrics-scroll-box textarea { | |
| height: 405px !important; /* 固定高度 */ | |
| max-height: 500px !important; /* 最大高度 */ | |
| overflow-y: auto !important; /* 垂直滚动 */ | |
| white-space: pre-wrap; /* 保留换行 */ | |
| line-height: 1.5; /* 行高优化 */ | |
| } | |
| .gr-examples { | |
| background: transparent !important; | |
| border: 1px solid #e0e0e0 !important; | |
| border-radius: 8px; | |
| margin: 1rem 0 !important; | |
| padding: 1rem !important; | |
| } | |
| """ | |
| with gr.Blocks(css=css) as demo: | |
| gr.HTML(f""" | |
| <div style="display: flex; align-items: center;"> | |
| <img src='https://raw.githubusercontent.com/ASLP-lab/DiffRhythm/refs/heads/main/src/DiffRhythm_logo.jpg' | |
| style='width: 200px; height: 40%; display: block; margin: 0 auto 20px;'> | |
| </div> | |
| <div style="flex: 1; text-align: center;"> | |
| <div style="font-size: 2em; font-weight: bold; text-align: center; margin-bottom: 5px"> | |
| Di♪♪Rhythm (谛韵) | |
| </div> | |
| <div style="display:flex; justify-content: center; column-gap:4px;"> | |
| <a href="https://arxiv.org/abs/2503.01183"> | |
| <img src='https://img.shields.io/badge/Arxiv-Paper-blue'> | |
| </a> | |
| <a href="https://github.com/ASLP-lab/DiffRhythm"> | |
| <img src='https://img.shields.io/badge/GitHub-Repo-green'> | |
| </a> | |
| <a href="https://aslp-lab.github.io/DiffRhythm.github.io/"> | |
| <img src='https://img.shields.io/badge/Project-Page-brown'> | |
| </a> | |
| </div> | |
| </div> | |
| """) | |
| with gr.Tabs() as tabs: | |
| # page 1 | |
| with gr.Tab("Music Generate", id=0): | |
| with gr.Row(): | |
| with gr.Column(): | |
| lrc = gr.Textbox( | |
| label="Lyrics", | |
| placeholder="Input the full lyrics", | |
| lines=12, | |
| max_lines=50, | |
| elem_classes="lyrics-scroll-box", | |
| value="""[00:04.074] Tell me that I'm special\n[00:06.226] Tell me I look pretty\n[00:08.175] Tell me I'm a little angel\n[00:10.175] Sweetheart of your city\n[00:13.307] Say what I'm dying to hear\n[00:17.058] 'Cause I'm dying to hear you\n[00:20.523] Tell me I'm that new thing\n[00:22.571] Tell me that I'm relevant\n[00:24.723] Tell me that I got a big heart\n[00:26.723] Then back it up with evidence\n[00:29.408] I need it and I don't know why\n[00:33.907] This late at night\n[00:36.139] Isn't it lonely\n[00:38.991] I'd do anything to make you want me\n[00:43.222] I'd give it all up if you told me\n[00:47.339] That I'd be\n[00:49.157] The number one girl in your eyes\n[00:52.506] Your one and only\n[00:55.437] So what's it gon' take for you to want me\n[00:59.589] I'd give it all up if you told me\n[01:03.674] That I'd be\n[01:05.823] The number one girl in your eyes\n[01:10.841] Tell me I'm going real big places\n[01:14.055] Down to earth, so friendly\n[01:16.105] And even through all the phases\n[01:18.256] Tell me you accept me\n[01:21.155] Well, that's all I'm dying to hear\n[01:24.937] Yeah, I'm dying to hear you\n[01:28.521] Tell me that you need me\n[01:30.437] Tell me that I'm loved\n[01:32.740] Tell me that I'm worth it\n[01:34.605] And that I'm enough\n[01:37.571] I need it and I don't know why\n[01:41.889] This late at night\n[01:43.805] Isn't it lonely\n[01:46.871] I'd do anything to make you want me\n[01:51.004] I'd give it all up if you told me\n[01:55.237] That I'd be\n[01:57.089] The number one girl in your eyes\n[02:00.325] Your one and only\n[02:03.305] So what's it gon' take for you to want me\n[02:07.355] I'd give it all up if you told me\n[02:11.589] That I'd be\n[02:13.623] The number one girl in your eyes\n[02:16.804] The girl in your eyes\n[02:20.823] The girl in your eyes\n[02:26.055] Tell me I'm the number one girl\n[02:28.355] I'm the number one girl in your eyes\n[02:33.172] The girl in your eyes\n[02:37.321] The girl in your eyes\n[02:42.472] Tell me I'm the number one girl\n[02:44.539] I'm the number one girl in your eyes\n[02:49.605] Well isn't it lonely\n[02:52.488] I'd do anything to make you want me\n[02:56.637] I'd give it all up if you told me\n[03:00.888] That I'd be\n[03:03.172] The number one girl in your eyes\n[03:06.272] Your one and only\n[03:09.160] So what's it gon' take for you to want me\n[03:13.056] I'd give it all up if you told me\n[03:17.305] That I'd be\n[03:19.488] The number one girl in your eyes\n[03:25.420] The number one girl in your eyes\n""" | |
| ) | |
| current_prompt_type = gr.State(value="audio") | |
| with gr.Tabs() as inside_tabs: | |
| with gr.Tab("Audio Prompt"): | |
| audio_prompt = gr.Audio(label="Audio Prompt", type="filepath", value="./src/prompt/default.wav") | |
| with gr.Tab("Text Prompt"): | |
| text_prompt = gr.Textbox( | |
| label="Text Prompt", | |
| placeholder="Enter the Text Prompt, eg: emotional piano pop", | |
| ) | |
| def update_prompt_type(evt: gr.SelectData): | |
| return "audio" if evt.index == 0 else "text" | |
| inside_tabs.select( | |
| fn=update_prompt_type, | |
| outputs=current_prompt_type | |
| ) | |
| with gr.Column(): | |
| with gr.Accordion("Best Practices Guide", open=True): | |
| gr.Markdown(""" | |
| 1. **Lyrics Format Requirements** | |
| - Each line must follow: `[mm:ss.xx]Lyric content` | |
| - Example of valid format: | |
| ``` | |
| [00:10.00]Moonlight spills through broken blinds | |
| [00:13.20]Your shadow dances on the dashboard shrine | |
| ``` | |
| 2. **Generation Duration Limits** | |
| - The generated music must be between **95 seconds (1:35)** and **285 seconds (4:45)** in length | |
| - The latest valid lyric timestamp cannot exceed **04:45.00 (285s)** | |
| 3. **Audio Prompt Requirements** | |
| - Reference audio should be ≥ 1 second, Audio >10 seconds will be randomly clipped into 10 seconds | |
| - For optimal results, the 10-second clips should be carefully selected | |
| - Shorter clips may lead to incoherent generation | |
| 4. **Supported Languages** | |
| - Chinese and English | |
| - More languages comming soon | |
| 5. **Others** | |
| - If loading audio result is slow, you can select Output Format as mp3 in Advanced Settings. | |
| """) | |
| # Music_Duration = gr.Radio(["95s", "285s"], label="Music Duration", value="95s") | |
| Music_Duration = gr.Slider( | |
| minimum=95, | |
| maximum=285, | |
| step=1, | |
| value=95, | |
| label="Music Duration (s)", | |
| interactive=True | |
| ) | |
| preference_infer = gr.Radio(["quality first", "speed first"], label="Preference", value="quality first") | |
| lyrics_btn = gr.Button("Generate", variant="primary") | |
| audio_output = gr.Audio(label="Audio Result", type="filepath", elem_id="audio_output") | |
| with gr.Accordion("Advanced Settings", open=False): | |
| seed = gr.Slider( | |
| label="Seed", | |
| minimum=0, | |
| maximum=MAX_SEED, | |
| step=1, | |
| value=0, | |
| ) | |
| randomize_seed = gr.Checkbox(label="Randomize seed", value=True) | |
| steps = gr.Slider( | |
| minimum=10, | |
| maximum=100, | |
| value=32, | |
| step=1, | |
| label="Diffusion Steps", | |
| interactive=True, | |
| elem_id="step_slider" | |
| ) | |
| cfg_strength = gr.Slider( | |
| minimum=1, | |
| maximum=10, | |
| value=4.0, | |
| step=0.5, | |
| label="CFG Strength", | |
| interactive=True, | |
| elem_id="step_slider" | |
| ) | |
| # edit = gr.Checkbox(label="edit", value=False) | |
| # edit = False | |
| # preference_infer = gr.Radio(["quality first", "speed first"], label="Preference", value="quality first") | |
| # edit_segments = gr.Textbox( | |
| # label="Edit Segments", | |
| # placeholder="Time segments to edit (in seconds). Format: `[[start1,end1],...]", | |
| # ) | |
| odeint_method = gr.Radio(["euler", "midpoint", "rk4","implicit_adams"], label="ODE Solver", value="euler") | |
| file_type = gr.Dropdown(["wav", "mp3", "ogg"], label="Output Format", value="mp3") | |
| gr.Examples( | |
| examples=[ | |
| ["./src/prompt/pop_cn.wav"], | |
| ["./src/prompt/pop_en.wav"], | |
| ["./src/prompt/rock_cn.wav"], | |
| ["./src/prompt/rock_en.wav"], | |
| ["./src/prompt/country_cn.wav"], | |
| ["./src/prompt/country_en.wav"], | |
| ["./src/prompt/classic_cn.wav"], | |
| ["./src/prompt/classic_en.wav"], | |
| ["./src/prompt/jazz_cn.wav"], | |
| ["./src/prompt/jazz_en.wav"], | |
| ["./src/prompt/rap_cn.wav"], | |
| ["./src/prompt/rap_en.wav"], | |
| ["./src/prompt/default.wav"] | |
| ], | |
| inputs=[audio_prompt], | |
| label="Audio Examples", | |
| examples_per_page=13, | |
| elem_id="audio-examples-container" | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["Pop Emotional Piano"], | |
| ["流行 情感 钢琴"], | |
| ["Indie folk ballad, coming-of-age themes, acoustic guitar picking with harmonica interludes"], | |
| ["独立民谣, 成长主题, 原声吉他弹奏与口琴间奏"] | |
| ], | |
| inputs=[text_prompt], | |
| label="Text Examples", | |
| examples_per_page=4, | |
| elem_id="text-examples-container" | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["""[00:04.074] Tell me that I'm special\n[00:06.226] Tell me I look pretty\n[00:08.175] Tell me I'm a little angel\n[00:10.175] Sweetheart of your city\n[00:13.307] Say what I'm dying to hear\n[00:17.058] 'Cause I'm dying to hear you\n[00:20.523] Tell me I'm that new thing\n[00:22.571] Tell me that I'm relevant\n[00:24.723] Tell me that I got a big heart\n[00:26.723] Then back it up with evidence\n[00:29.408] I need it and I don't know why\n[00:33.907] This late at night\n[00:36.139] Isn't it lonely\n[00:38.991] I'd do anything to make you want me\n[00:43.222] I'd give it all up if you told me\n[00:47.339] That I'd be\n[00:49.157] The number one girl in your eyes\n[00:52.506] Your one and only\n[00:55.437] So what's it gon' take for you to want me\n[00:59.589] I'd give it all up if you told me\n[01:03.674] That I'd be\n[01:05.823] The number one girl in your eyes\n[01:10.841] Tell me I'm going real big places\n[01:14.055] Down to earth, so friendly\n[01:16.105] And even through all the phases\n[01:18.256] Tell me you accept me\n[01:21.155] Well, that's all I'm dying to hear\n[01:24.937] Yeah, I'm dying to hear you\n[01:28.521] Tell me that you need me\n[01:30.437] Tell me that I'm loved\n[01:32.740] Tell me that I'm worth it\n[01:34.605] And that I'm enough\n[01:37.571] I need it and I don't know why\n[01:41.889] This late at night\n[01:43.805] Isn't it lonely\n[01:46.871] I'd do anything to make you want me\n[01:51.004] I'd give it all up if you told me\n[01:55.237] That I'd be\n[01:57.089] The number one girl in your eyes\n[02:00.325] Your one and only\n[02:03.305] So what's it gon' take for you to want me\n[02:07.355] I'd give it all up if you told me\n[02:11.589] That I'd be\n[02:13.623] The number one girl in your eyes\n[02:16.804] The girl in your eyes\n[02:20.823] The girl in your eyes\n[02:26.055] Tell me I'm the number one girl\n[02:28.355] I'm the number one girl in your eyes\n[02:33.172] The girl in your eyes\n[02:37.321] The girl in your eyes\n[02:42.472] Tell me I'm the number one girl\n[02:44.539] I'm the number one girl in your eyes\n[02:49.605] Well isn't it lonely\n[02:52.488] I'd do anything to make you want me\n[02:56.637] I'd give it all up if you told me\n[03:00.888] That I'd be\n[03:03.172] The number one girl in your eyes\n[03:06.272] Your one and only\n[03:09.160] So what's it gon' take for you to want me\n[03:13.056] I'd give it all up if you told me\n[03:17.305] That I'd be\n[03:19.488] The number one girl in your eyes\n[03:25.420] The number one girl in your eyes\n"""], | |
| ["""[00:00.133]Abracadabra, abracadabra\n[00:03.985]Abracadabra, abracadabra\n[00:15.358]Pay the toll to the angels\n[00:18.694]Drawin' circles in the clouds\n[00:22.966]Keep your mind on the distance\n[00:26.321]When the devil turns around\n[00:30.540]Hold me in your heart tonight\n[00:33.751]In the magic of the dark moonlight\n[00:38.189]Save me from this empty fight\n[00:43.521]In the game of life\n[00:45.409]Like a poem said by a lady in red\n[00:49.088]You hear the last few words of your life\n[00:53.013]With a haunting dance, now you're both in a trance\n[00:56.687]It's time to cast your spell on the night\n[01:01.131]Abracadabra amor-oo-na-na\n[01:04.394]Abracadabra morta-oo-gaga\n[01:08.778]Abracadabra, abra-ooh-na-na\n[01:12.063]In her tongue, she's sayin'\n[01:14.367]Death or love tonight\n[01:18.249]Abracadabra, abracadabra\n[01:22.136]Abracadabra, abracadabra\n[01:25.859]Feel the beat under your feet\n[01:27.554]The floor's on fire\n[01:29.714]Abracadabra, abracadabra\n[01:33.464]Choose the road on the west side\n[01:36.818]As the dust flies, watch it burn\n[01:41.057]Don't waste time on feeling\n[01:44.419]Use your passion no return\n[01:48.724]Hold me in your heart tonight\n[01:51.886]In the magic of the dark moonlight\n[01:56.270]Save me from this empty fight\n[02:01.599]In the game of life\n[02:03.524]Like a poem said by a lady in red\n[02:07.192]You hear the last few words of your life\n[02:11.055]With a haunting dance, now you're both in a trance\n[02:14.786]It's time to cast your spell on the night\n[02:19.225]Abracadabra amor-oo-na-na\n[02:22.553]Abracadabra morta-oo-gaga\n[02:26.852]Abracadabra, abra-ooh-na-na\n[02:30.110]In her tongue, she's sayin'\n[02:32.494]Death or love tonight\n[02:36.244]Abracadabra, abracadabra\n[02:40.161]Abracadabra, abracadabra\n[02:43.966]Feel the beat under your feet\n[02:45.630]The floor's on fire\n[02:47.812]Abracadabra, abracadabra\n[02:50.537]Phantom of the dancefloor, come to me\n[02:58.169]Sing for me a sinful melody\n[03:05.833]Ah-ah-ah-ah-ah, ah-ah, ah-ah\n[03:13.453]Ah-ah-ah-ah-ah, ah-ah, ah-ah\n[03:22.025]Abracadabra amor-oo-na-na\n[03:25.423]Abracadabra morta-oo-gaga\n[03:29.674]Abracadabra, abra-ooh-na-na\n[03:33.013]In her tongue, she's sayin'\n[03:35.401]Death or love tonight\n"""], | |
| ["""[00:00.27]只因你太美 baby 只因你太美 baby\n[00:08.95]只因你实在是太美 baby\n[00:13.99]只因你太美 baby\n[00:18.89]迎面走来的你让我如此蠢蠢欲动\n[00:20.88]这种感觉我从未有\n[00:21.79]Cause I got a crush on you who you\n[00:25.74]你是我的我是你的谁\n[00:28.09]再多一眼看一眼就会爆炸\n[00:30.31]再近一点靠近点快被融化\n[00:32.49]想要把你占为己有 baby bae\n[00:34.60]不管走到哪里\n[00:35.44]都会想起的人是你 you you\n[00:38.12]我应该拿你怎样\n[00:39.61]Uh 所有人都在看着你\n[00:42.36]我的心总是不安\n[00:44.18]Oh 我现在已病入膏肓\n[00:46.63]Eh oh\n[00:47.84]难道真的因你而疯狂吗\n[00:51.57]我本来不是这种人\n[00:53.59]因你变成奇怪的人\n[00:55.77]第一次呀变成这样的我\n[01:01.23]不管我怎么去否认\n[01:03.21]只因你太美 baby 只因你太美 baby\n[01:11.46]只因你实在是太美 baby\n[01:16.75]只因你太美 baby\n[01:21.09]Oh eh oh\n[01:22.82]现在确认地告诉我\n[01:25.26]Oh eh oh\n[01:27.31]你到底属于谁\n[01:29.98]Oh eh oh\n[01:31.70]现在确认地告诉我\n[01:34.45]Oh eh oh\n"""], | |
| ["""[00:19.50]也想不到要怎么问你别来无恙\n[00:25.71]世界乱的一塌糊涂可是能怎样\n[00:31.85]偶尔抬起头来还好有颗月亮可赏\n[00:38.96]太多回忆要我怎么摆进行李箱\n[00:45.22]一直没哭一直走路走灰多少太阳\n[00:51.70]因为往事没有办法悬赏 隐形在那大街小巷\n[01:00.22]剪断了它还嚣张\n[01:03.85]我的嘴在说谎 说的那么漂亮\n[01:10.07]说我早就忘了你像月一样的俏脸庞\n[01:16.51]最怕一边忙呀忙一边回想那旧时光\n[01:22.87]剪不掉的是你 带泪的脸 还真是烦\n[01:43.32]多少原因将我绑在半夜屋顶上\n[01:49.23]一直没再爱一个人如今就是这样\n[01:55.75]因为故事跟你说了一半 于是搁在所谓云端\n[02:04.21]谁忘不了谁孤单\n[02:07.79]我的心在说谎 说下去会疯狂\n[02:14.02]如果没有月亮那些日子都无妨\n[02:20.43]最怕一边忙呀忙一边想那旧时光\n[02:26.91]剪不掉的是你 带笑的苦 还真烦\n[02:33.81]我的嘴又说了谎 说的那么漂亮\n[02:39.68]以为已经忘了你的那些美像月光它剪不断\n[02:47.15]因为爱早就钻进心脏 心一跳泪就会烫\n[02:52.22]那些带泪的脸 带笑的苦 还真烦\n[02:59.28]月亮是个凶手 想你的我 是通缉犯\n[03:08.03]我有时候真的很怕望见那月光中的你\n"""] | |
| ], | |
| inputs=[lrc], | |
| label="Lrc Examples", | |
| examples_per_page=4, | |
| elem_id="lrc-examples-container", | |
| ) | |
| # page 2 | |
| with gr.Tab("Lyrics Generate", id=1): | |
| with gr.Row(): | |
| with gr.Column(): | |
| with gr.Accordion("Notice", open=False): | |
| gr.Markdown("**Two Generation Modes:**\n1. Generate from theme & tags\n2. Add timestamps to existing lyrics") | |
| with gr.Group(): | |
| gr.Markdown("### Method 1: Generate from Theme") | |
| theme = gr.Textbox(label="theme", placeholder="Enter song theme, e.g: Love and Heartbreak") | |
| tags_gen = gr.Textbox(label="tags", placeholder="Enter song tags, e.g: pop confidence healing") | |
| language = gr.Radio(["cn", "en"], label="Language", value="en") | |
| gen_from_theme_btn = gr.Button("Generate LRC (From Theme)", variant="primary") | |
| gr.Examples( | |
| examples=[ | |
| [ | |
| "Love and Heartbreak", | |
| "vocal emotional piano pop", | |
| "en" | |
| ], | |
| [ | |
| "Heroic Epic", | |
| "choir orchestral powerful", | |
| "cn" | |
| ] | |
| ], | |
| inputs=[theme, tags_gen, language], | |
| label="Examples: Generate from Theme" | |
| ) | |
| with gr.Group(visible=True): | |
| gr.Markdown("### Method 2: Add Timestamps to Lyrics") | |
| tags_lyrics = gr.Textbox(label="tags", placeholder="Enter song tags, e.g: ballad piano slow") | |
| lyrics_input = gr.Textbox( | |
| label="Raw Lyrics (without timestamps)", | |
| placeholder="Enter plain lyrics (without timestamps), e.g:\nYesterday\nAll my troubles...", | |
| lines=10, | |
| max_lines=50, | |
| elem_classes="lyrics-scroll-box" | |
| ) | |
| gen_from_lyrics_btn = gr.Button("Generate LRC (From Lyrics)", variant="primary") | |
| gr.Examples( | |
| examples=[ | |
| [ | |
| "acoustic folk happy", | |
| """I'm sitting here in the boring room\nIt's just another rainy Sunday afternoon""" | |
| ], | |
| [ | |
| "electronic dance energetic", | |
| """We're living in a material world\nAnd I am a material girl""" | |
| ] | |
| ], | |
| inputs=[tags_lyrics, lyrics_input], | |
| label="Examples: Generate from Lyrics" | |
| ) | |
| with gr.Column(): | |
| lrc_output = gr.Textbox( | |
| label="Generated LRC", | |
| placeholder="Timed lyrics will appear here", | |
| lines=57, | |
| elem_classes="lrc-output", | |
| show_copy_button=True | |
| ) | |
| # Bind functions | |
| gen_from_theme_btn.click( | |
| fn=R1_infer1, | |
| inputs=[theme, tags_gen, language], | |
| outputs=lrc_output | |
| ) | |
| gen_from_lyrics_btn.click( | |
| fn=R1_infer2, | |
| inputs=[tags_lyrics, lyrics_input], | |
| outputs=lrc_output | |
| ) | |
| tabs.select( | |
| lambda s: None, | |
| None, | |
| None | |
| ) | |
| lyrics_btn.click( | |
| fn=infer_music, | |
| inputs=[lrc, audio_prompt, text_prompt, current_prompt_type, seed, randomize_seed, steps, cfg_strength, file_type, odeint_method, preference_infer, Music_Duration], | |
| outputs=audio_output | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() |