""" YingMusic Singer - Gradio Web Interface ======================================== 基于参考音色与旋律音频的歌声合成系统，支持自动分离人声与伴奏。 A singing voice synthesis system powered by YingMusicSinger, with built-in vocal/accompaniment separation via MelBandRoformer. """ try: import spaces except ImportError: spaces = None import os import tempfile import gradio as gr import torch import torchaudio from initialization import download_files IS_HF_SPACE = os.environ.get("SPACE_ID") is not None HF_ENABLE = False LOCAL_DEVICE = "cuda" if torch.cuda.is_available() else "cpu" def local_move2gpu(x): """Move models to GPU on local environment. No-op on HuggingFace Spaces (ZeroGPU handles it).""" if IS_HF_SPACE: return x return x.to(LOCAL_DEVICE) # --------------------------------------------------------------------------- # Model loading (lazy, singleton) / 模型懒加载（单例） # --------------------------------------------------------------------------- _model = None _separator = None def _load_model_impl(): """Internal: load YingMusicSinger (no GPU decorator, called inside GPU context).""" download_files(task="infer") global _model if _model is None: from src.YingMusicSinger.infer.YingMusicSinger import YingMusicSinger _model = YingMusicSinger.from_pretrained("ASLP-lab/YingMusic-Singer") _model = local_move2gpu(_model) _model.eval() return _model def _load_separator_impl(): """Internal: load MelBandRoformer separator (no GPU decorator, called inside GPU context).""" download_files(task="infer") global _separator if _separator is None: from src.third_party.MusicSourceSeparationTraining.inference_api import Separator _separator = Separator( config_path="ckpts/config_vocals_mel_band_roformer_kj.yaml", checkpoint_path="ckpts/MelBandRoformer.ckpt", ) return _separator # --------------------------------------------------------------------------- # Vocal separation utilities / 人声分离工具 # --------------------------------------------------------------------------- def _separate_vocals_impl(audio_path: str) -> tuple: """ Separate audio into vocals and accompaniment using MelBandRoformer. Must be called within an active GPU context. """ separator = _load_separator_impl() wav, sr = torchaudio.load(audio_path) vocal_wav, inst_wav, out_sr = separator.separate(wav, sr) tmp_dir = tempfile.mkdtemp() vocals_path = os.path.join(tmp_dir, "vocals.wav") accomp_path = os.path.join(tmp_dir, "accompaniment.wav") torchaudio.save(vocals_path, torch.from_numpy(vocal_wav), out_sr) torchaudio.save(accomp_path, torch.from_numpy(inst_wav), out_sr) return vocals_path, accomp_path def mix_vocal_and_accompaniment( vocal_path: str, accomp_path: str, vocal_gain: float = 1.0, ) -> str: """ 将合成人声与伴奏混合为最终音频。 Mix synthesised vocals with accompaniment into a final audio file. """ vocal_wav, vocal_sr = torchaudio.load(vocal_path) accomp_wav, accomp_sr = torchaudio.load(accomp_path) if accomp_sr != vocal_sr: accomp_wav = torchaudio.functional.resample(accomp_wav, accomp_sr, vocal_sr) if vocal_wav.shape[0] != accomp_wav.shape[0]: if vocal_wav.shape[0] == 1: vocal_wav = vocal_wav.expand(accomp_wav.shape[0], -1) else: accomp_wav = accomp_wav.expand(vocal_wav.shape[0], -1) min_len = min(vocal_wav.shape[1], accomp_wav.shape[1]) vocal_wav = vocal_wav[:, :min_len] accomp_wav = accomp_wav[:, :min_len] mixed = vocal_wav * vocal_gain + accomp_wav peak = mixed.abs().max() if peak > 1.0: mixed = mixed / peak out_path = os.path.join(tempfile.mkdtemp(), "mixed_output.wav") torchaudio.save(out_path, mixed, sample_rate=vocal_sr) return out_path # --------------------------------------------------------------------------- # Inference wrapper / 推理入口 # Single @spaces.GPU scope covers ALL heavy work (separation + synthesis) # so models stay resident in GPU memory across steps within one call. # --------------------------------------------------------------------------- @spaces.GPU def synthesize( ref_audio, melody_audio, ref_text, target_text, separate_vocals_flag, mix_accompaniment_flag, sil_len_to_end, t_shift, nfe_step, cfg_strength, seed, ): """ 主合成流程 / Main synthesis pipeline. 1. (可选) 用 MelBandRoformer 分离参考音频和旋律音频的人声与伴奏 2. 送入 YingMusicSinger 合成 3. (可选) 将合成人声与旋律音频的伴奏混合 """ import random # ---- 输入校验 / Input validation ---------------------------------------- if ref_audio is None: raise gr.Error("请上传参考音频 / Please upload Reference Audio") if melody_audio is None: raise gr.Error("请上传旋律音频 / Please upload Melody Audio") if not ref_text.strip(): raise gr.Error("请输入参考音频对应的歌词 / Please enter Reference Text") if not target_text.strip(): raise gr.Error("请输入目标合成歌词 / Please enter Target Text") ref_audio_path = ref_audio if isinstance(ref_audio, str) else ref_audio[0] melody_audio_path = ( melody_audio if isinstance(melody_audio, str) else melody_audio[0] ) actual_seed = int(seed) if actual_seed < 0: actual_seed = random.randint(0, 2**31 - 1) # ---- Step 1: 人声分离（合并在同一 GPU 上下文中）/ Vocal separation (same GPU context) ---- melody_accomp_path = None actual_ref_path = ref_audio_path actual_melody_path = melody_audio_path if separate_vocals_flag: ref_vocals_path, _ = _separate_vocals_impl(ref_audio_path) actual_ref_path = ref_vocals_path melody_vocals_path, melody_accomp_path = _separate_vocals_impl(melody_audio_path) actual_melody_path = melody_vocals_path # ---- Step 2: 模型推理 / Model inference (same GPU context) --------------- model = _load_model_impl() audio_tensor, sr = model( ref_audio_path=actual_ref_path, melody_audio_path=actual_melody_path, ref_text=ref_text.strip(), target_text=target_text.strip(), lrc_align_mode="sentence_level", sil_len_to_end=float(sil_len_to_end), t_shift=float(t_shift), nfe_step=int(nfe_step), cfg_strength=float(cfg_strength), seed=actual_seed, ) vocal_out_path = os.path.join(tempfile.mkdtemp(), "vocal_output.wav") torchaudio.save(vocal_out_path, audio_tensor.to("cpu"), sample_rate=sr) # ---- Step 3: 混合伴奏 / Mix accompaniment (optional) --------------------- if ( separate_vocals_flag and mix_accompaniment_flag and melody_accomp_path is not None ): final_path = mix_vocal_and_accompaniment(vocal_out_path, melody_accomp_path) return final_path else: return vocal_out_path # --------------------------------------------------------------------------- # Example presets / 预设示例 # --------------------------------------------------------------------------- EXAMPLES_MELODY_CONTROL = [ # [ref_audio, melody_audio, ref_text, target_text, sep, mix, sil, t_shift, nfe, cfg, seed] [ "examples/melody_control/ref_01.wav", "examples/melody_control/melody_01.wav", "该体谅的不执着|如果那天我", "好多天|看不完你", True, False, 0.5, 0.5, 32, 3.0, -1, ], [ "examples/melody_control/ref_02.wav", "examples/melody_control/melody_02.wav", "月光下的身影|渐渐模糊", "星光照亮前路|指引方向", True, False, 0.5, 0.5, 32, 3.0, -1, ], ] EXAMPLES_LYRIC_EDIT = [ [ "examples/lyric_edit/ref_01.wav", "examples/lyric_edit/melody_01.wav", "该体谅的不执着|如果那天我", "忘不掉的笑容|留在心里面", True, False, 0.5, 0.5, 32, 3.0, -1, ], [ "examples/lyric_edit/ref_02.wav", "examples/lyric_edit/melody_02.wav", "夜深了还不睡|想着你的脸", "春风又吹过来|带走我思念", True, False, 0.5, 0.5, 32, 3.0, -1, ], ] # --------------------------------------------------------------------------- # Custom CSS / 自定义样式 # --------------------------------------------------------------------------- CUSTOM_CSS = """ @import url('https://fonts.googleapis.com/css2?family=DM+Sans:ital,opsz,wght@0,9..40,300;0,9..40,500;0,9..40,700;1,9..40,400&family=Playfair+Display:wght@600;800&display=swap'); :root { --primary: #e85d04; --primary-light: #f48c06; --bg-dark: #0d1117; --surface: #161b22; --surface-light: #21262d; --text: #f0f6fc; --text-muted: #8b949e; --accent-glow: rgba(232, 93, 4, 0.15); --border: #30363d; } .gradio-container { font-family: 'DM Sans', sans-serif !important; max-width: 1100px !important; margin: auto !important; } /* ---------- Badge links: no underline, no gap artifacts ---------- */ #app-header .badges a { text-decoration: none !important; display: inline-block; line-height: 0; margin: 3px 2px; } #app-header .badges a img, #app-header .badges > img { display: inline-block; vertical-align: middle; margin: 0; } #app-header .badges { line-height: 1.8; } /* ---------- Header / 头部 ---------- */ #app-header { text-align: center; padding: 1.8rem 1rem 0.5rem; } #app-header h1 { font-size: 1.45rem !important; font-weight: 700 !important; line-height: 1.4; margin-bottom: 0.6rem !important; } #app-header .badges img { display: inline-block; margin: 3px 2px; vertical-align: middle; } #app-header .authors { color: var(--text-muted); font-size: 0.92rem; margin: 0.5rem 0 0.2rem; line-height: 1.7; } #app-header .affiliations { color: var(--text-muted); font-size: 0.85rem; margin-bottom: 0.5rem; } #app-header .lang-links a { color: var(--primary-light); text-decoration: none; margin: 0 4px; font-size: 0.9rem; } #app-header .lang-links a:hover { text-decoration: underline; } /* ---------- Disclaimer ---------- */ #disclaimer { border-top: 1px solid var(--border); margin: 24px 0 4px; padding: 14px 4px 4px; font-size: 0.80rem; color: #6e7681; line-height: 1.65; } #disclaimer strong { color: #8b949e; font-weight: 600; } /* ---------- Section labels / 分区标题 ---------- */ .section-title { font-family: 'DM Sans', sans-serif !important; font-weight: 700 !important; font-size: 1rem !important; letter-spacing: 0.06em; text-transform: uppercase; color: var(--primary-light) !important; border-bottom: 2px solid var(--primary); padding-bottom: 6px; margin-bottom: 12px !important; } /* ---------- Example tabs ---------- */ .example-tab-label { font-weight: 600 !important; font-size: 0.95rem !important; } /* ---------- Run button / 合成按钮 ---------- */ #run-btn { background: linear-gradient(135deg, #e85d04, #dc2f02) !important; border: none !important; color: #fff !important; font-weight: 700 !important; font-size: 1.1rem !important; letter-spacing: 0.04em; padding: 12px 0 !important; border-radius: 10px !important; transition: transform 0.15s, box-shadow 0.25s !important; box-shadow: 0 4px 20px rgba(232, 93, 4, 0.35) !important; } #run-btn:hover { transform: translateY(-1px) !important; box-shadow: 0 6px 28px rgba(232, 93, 4, 0.5) !important; } /* ---------- Output audio / 输出音频 ---------- */ #output-audio { border: 2px solid var(--primary) !important; border-radius: 12px !important; background: var(--accent-glow) !important; } """ # --------------------------------------------------------------------------- # Header HTML / 头部 HTML # --------------------------------------------------------------------------- HEADER_HTML = """

🎤 YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Python License arXiv GitHub HuggingFace Space HuggingFace Model LyricEditBench Discord WeChat ASLP Lab

Chunbo Hao¹²  ·  Junjie Zheng²  ·  Guobin Ma¹  ·  Yuepeng Jiang¹  ·  Huakang Chen¹  ·  Wenjie Tian¹  ·  Gongyu Chen²  ·  Zihao Chen²  ·  Lei Xie¹

1 Northwestern Polytechnical University  ·  2 Giant Network

""" DISCLAIMER_HTML = """
Disclaimer / 免责声明
YingMusic-Singer enables the creation of singing voices with modified lyrics, supporting applications in artistic creation and entertainment. Potential risks include unauthorized voice cloning and copyright infringement. To ensure responsible deployment, users should obtain consent for voice usage, disclose AI involvement, and verify musical originality.
YingMusic-Singer 可用于修改歌词后的歌声合成，支持艺术创作与娱乐应用。潜在风险包括未经授权的声音克隆与版权侵权。为确保负责任地使用，用户应在使用他人声音前获得授权、公开 AI 参与情况，并确认音乐内容的原创性。
""" # --------------------------------------------------------------------------- # Build the Gradio UI / 构建界面 # --------------------------------------------------------------------------- def build_ui(): # Shared input components referenced by both Examples tabs and main form ALL_INPUTS_ORDER = None # defined after components are created with gr.Blocks( css=CUSTOM_CSS, title="YingMusic Singer", theme=gr.themes.Base() ) as demo: # ---- Header / 头部 ---- gr.HTML(HEADER_HTML) gr.HTML("
") # ================================================================ # ROW 1 – 音频输入 / Audio Inputs + 歌词 / Lyrics (side by side) # ================================================================ with gr.Row(equal_height=True): # ---- 左栏：音频上传 / Left column: audio uploads ---- with gr.Column(scale=1): gr.Markdown( "#### 🎙️ 音频输入 / Audio Inputs", elem_classes="section-title" ) ref_audio = gr.Audio( label="参考音频 / Reference Audio（提供音色 / provides timbre）", type="filepath", ) melody_audio = gr.Audio( label="旋律音频 / Melody Audio（提供旋律与时长 / provides melody & duration）", type="filepath", ) # ---- 右栏：歌词 / Right column: lyrics ---- with gr.Column(scale=1): gr.Markdown("#### ✏️ 歌词 / Lyrics", elem_classes="section-title") ref_text = gr.Textbox( label="参考音频歌词 / Reference Text", placeholder="例如 / e.g.：该体谅的不执着|如果那天我", lines=5, ) target_text = gr.Textbox( label="目标合成歌词 / Target Text", placeholder="例如 / e.g.：好多天|看不完你", lines=5, ) # --------------------------------------------------------------------------- # Build the Gradio UI / 构建界面 # --------------------------------------------------------------------------- def build_ui(): with gr.Blocks( css=CUSTOM_CSS, title="YingMusic Singer", theme=gr.themes.Base() ) as demo: # ---- Header ---- gr.HTML(HEADER_HTML) gr.HTML("
") # ================================================================ # ROW 1 – 音频输入 + 歌词 # ================================================================ with gr.Row(equal_height=True): with gr.Column(scale=1): gr.Markdown("#### 🎙️ 音频输入 / Audio Inputs", elem_classes="section-title") ref_audio = gr.Audio( label="参考音频 / Reference Audio（提供音色 / provides timbre）", type="filepath", ) melody_audio = gr.Audio( label="旋律音频 / Melody Audio（提供旋律与时长 / provides melody & duration）", type="filepath", ) with gr.Column(scale=1): gr.Markdown("#### ✏️ 歌词 / Lyrics", elem_classes="section-title") ref_text = gr.Textbox( label="参考音频歌词 / Reference Text", placeholder="例如 / e.g.：该体谅的不执着|如果那天我", lines=5, ) target_text = gr.Textbox( label="目标合成歌词 / Target Text", placeholder="例如 / e.g.：好多天|看不完你", lines=5, ) # ================================================================ # ROW 2 – 预设示例 / Example Presets ← before vocal separation # ================================================================ gr.HTML("
") gr.Markdown("#### 🎵 预设示例 / Example Presets", elem_classes="section-title") gr.Markdown( "点击任意行自动填入输入区域 / Click any row to auto-fill the inputs above" ) # Hidden advanced-param components so gr.Examples can reference them # (real sliders rendered inside the accordion below override these values) with gr.Row(visible=False): _sep_flag_ex = gr.Checkbox(value=True) _mix_flag_ex = gr.Checkbox(value=False) _sil_ex = gr.Number(value=0.5) _tshift_ex = gr.Number(value=0.5) _nfe_ex = gr.Number(value=32) _cfg_ex = gr.Number(value=3.0) _seed_ex = gr.Number(value=-1, precision=0) _example_inputs = [ ref_audio, melody_audio, ref_text, target_text, _sep_flag_ex, _mix_flag_ex, _sil_ex, _tshift_ex, _nfe_ex, _cfg_ex, _seed_ex, ] with gr.Tabs(): with gr.Tab("🎼 Melody Control"): gr.Examples( examples=EXAMPLES_MELODY_CONTROL, inputs=_example_inputs, label="Melody Control Examples", examples_per_page=5, ) with gr.Tab("✏️ Lyric Edit"): gr.Examples( examples=EXAMPLES_LYRIC_EDIT, inputs=_example_inputs, label="Lyric Edit Examples", examples_per_page=5, ) # ================================================================ # ROW 3 – 伴奏分离 / Vocal Separation # ================================================================ gr.HTML("
") gr.Markdown("#### 🎚️ 伴奏分离 / Vocal Separation", elem_classes="section-title") with gr.Row(): separate_vocals_flag = gr.Checkbox( value=True, label="分离人声后过模型 / Separate vocals before synthesis", info=( "从参考音频和旋律音频中分离人声，仅用人声送入模型 / " "Extract vocals from both reference and melody audio before feeding into the model" ), ) mix_accompaniment_flag = gr.Checkbox( value=False, interactive=True, label="输出时混入伴奏 / Mix accompaniment into output", info=( "将合成人声与分离出的伴奏混合输出（需先开启人声分离）/ " "Mix synthesised vocals with separated accompaniment (requires vocal separation)" ), ) # ================================================================ # ROW 4 – 高级参数 / Advanced Parameters (collapsible) # ================================================================ with gr.Accordion("⚙️ 高级参数 / Advanced Parameters", open=False): with gr.Row(): nfe_step = gr.Slider( minimum=4, maximum=128, value=32, step=1, label="采样步数 / NFE Steps", info="更多步数 = 更高质量，但更慢 / More steps = higher quality, but slower", ) cfg_strength = gr.Slider( minimum=0.0, maximum=10.0, value=3.0, step=0.1, label="CFG 强度 / CFG Strength", ) t_shift = gr.Slider( minimum=0.0, maximum=1.0, value=0.5, step=0.01, label="采样时间偏移 / t‑shift", ) with gr.Row(): sil_len_to_end = gr.Slider( minimum=0.0, maximum=3.0, value=0.5, step=0.1, label="末尾静音时长 (秒) / Silence Padding (s)", ) seed = gr.Number( value=-1, precision=0, label="随机种子 / Random Seed", info="-1 表示随机 / -1 means random", ) # ================================================================ # ROW 5 – 合成按钮与输出 / Run & Output # ================================================================ gr.HTML("
") run_btn = gr.Button("🎤 开始合成 / Synthesize", elem_id="run-btn", size="lg") output_audio = gr.Audio( label="合成结果 / Generated Audio", type="filepath", elem_id="output-audio", ) # All inputs for the synthesize() call (uses real sliders, not example placeholders) _all_inputs = [ ref_audio, melody_audio, ref_text, target_text, separate_vocals_flag, mix_accompaniment_flag, sil_len_to_end, t_shift, nfe_step, cfg_strength, seed, ] # ================================================================ # Event wiring / 事件绑定 # ================================================================ separate_vocals_flag.change( fn=lambda sep: gr.update(interactive=sep, value=False), inputs=[separate_vocals_flag], outputs=[mix_accompaniment_flag], ) run_btn.click( fn=synthesize, inputs=_all_inputs, outputs=output_audio, ) # ---- 页脚：免责声明 / Footer: disclaimer ---- gr.HTML(DISCLAIMER_HTML) return demo # --------------------------------------------------------------------------- # Entry point / 启动入口 # --------------------------------------------------------------------------- if __name__ == "__main__": demo = build_ui() demo.queue() demo.launch(server_name="0.0.0.0", server_port=7860, share=False)