Duplicate from ASLP-lab/YingMusic-Singer-Plus

Co-authored-by: ASLP-lab <ASLP-lab@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+license: cc-by-4.0
+datasets:
+- ASLP-lab/LyricEditBench
+language:
+- zh
+- en
+---
+
+
+<div align="center">
+
+<h1>🎤 YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance</h1>
+
+<p>
+  <a href="">English</a> ｜ <a href="README_ZH.md">中文</a>
+</p>
+
+
+
+![Python](https://img.shields.io/badge/Python-3.10-3776AB?logo=python&logoColor=white)
+![License](https://img.shields.io/badge/License-CC--BY--4.0-lightgrey)
+
+[![arXiv Paper](https://img.shields.io/badge/arXiv-2603.24589-b31b1b?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2603.24589)
+[![GitHub](https://img.shields.io/badge/GitHub-YingMusic--Singer-181717?logo=github&logoColor=white)](https://github.com/ASLP-lab/YingMusic-Singer-Plus)
+[![Demo Page](https://img.shields.io/badge/GitHub-Demo--Page-8A2BE2?logo=github&logoColor=white&labelColor=181717)](https://aslp-lab.github.io/YingMusic-Singer-Plus-Demo/)
+[![HuggingFace Space](https://img.shields.io/badge/🤗%20HuggingFace-Space-FFD21E)](https://huggingface.co/spaces/ASLP-lab/YingMusic-Singer-Plus)
+[![HuggingFace Model](https://img.shields.io/badge/🤗%20HuggingFace-Model-FF9D00)](https://huggingface.co/ASLP-lab/YingMusic-Singer-Plus)
+[![Dataset LyricEditBench](https://img.shields.io/badge/🤗%20HuggingFace-LyricEditBench-FF6F00)](https://huggingface.co/datasets/ASLP-lab/LyricEditBench)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/RXghgWyvrn)
+[![WeChat](https://img.shields.io/badge/WeChat-Group-07C160?logo=wechat&logoColor=white)](https://github.com/ASLP-lab/YingMusic-Singer-Plus/blob/main/assets/wechat_qr.png)
+[![Lab](https://img.shields.io/badge/🏫%20ASLP-Lab-4A90D9)](http://www.npu-aslp.org/)
+<p>
+        <a href="https://orcid.org/0009-0005-5957-8936">Chunbo Hao</a><sup>1,2</sup> ·
+        <a href="https://orcid.org/0009-0003-2602-2910">Junjie Zheng</a><sup>2</sup> ·
+        <a href="https://orcid.org/0009-0001-6706-0572">Guobin Ma</a><sup>1</sup> ·
+        Yuepeng Jiang<sup>1</sup> ·
+        Huakang Chen<sup>1</sup> ·
+        Wenjie Tian<sup>1</sup> ·
+        <a href="https://orcid.org/0009-0003-9258-4006">Gongyu Chen</a><sup>2</sup> ·
+        <a href="https://orcid.org/0009-0005-5413-6725">Zihao Chen</a><sup>2</sup> ·
+        Lei Xie<sup>1</sup>
+</p>
+<p>
+        <sup>1</sup> Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, China<br>
+        <sup>2</sup> AI Lab, GiantNetwork, China
+</p>
+
+
+</div>
+
+-----
+
+## 🌟 About This Repository
+
+The root directory contains the packaged model weights saved via `ModelHubMixin` in safetensor format. The `ckpts/` folder holds individual component checkpoints for downstream development and custom integration.
+
+## 🚀 Getting Started
+
+Full documentation and deployment guides are available at our GitHub repository:
+👉 [https://github.com/ASLP-lab/YingMusic-Singer-Plus](https://github.com/ASLP-lab/YingMusic-Singer-Plus)
+
+We support multiple deployment options to fit your workflow.
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/ASLP-lab/YingMusic-Singer-Plus/main/assets/institutional_logo.svg" alt="Institutional Logo" width="600">
+</p>

ckpts/MelBandRoformer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87201f4d31afb5bc79993230fc49446918425574db48c01c405e44f365c7559e
+size 913106900

ckpts/YingMusicSinger_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0684557abcdb00ee9e39cb351d5b9b90b98773ab6630d00fa27daa0e51ab56
+size 8133498835

ckpts/config_vocals_mel_band_roformer_kj.yaml

@@ -0,0 +1,72 @@
+audio:
+  chunk_size: 352800
+  dim_f: 1024
+  dim_t: 256
+  hop_length: 441
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.000
+
+model:
+  dim: 384
+  depth: 6
+  stereo: true
+  num_stems: 1
+  time_transformer_depth: 1
+  freq_transformer_depth: 1
+  num_bands: 60
+  dim_head: 64
+  heads: 8
+  attn_dropout: 0
+  ff_dropout: 0
+  flash_attn: True
+  dim_freqs_in: 1025
+  sample_rate: 44100  # needed for mel filter bank from librosa
+  stft_n_fft: 2048
+  stft_hop_length: 441
+  stft_win_length: 2048
+  stft_normalized: False
+  mask_estimator_depth: 2
+  multi_stft_resolution_loss_weight: 1.0
+  multi_stft_resolutions_window_sizes: !!python/tuple
+  - 4096
+  - 2048
+  - 1024
+  - 512
+  - 256
+  multi_stft_hop_size: 147
+  multi_stft_normalized: False
+
+training:
+  batch_size: 4
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+  - vocals
+  - other
+  lr: 1.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: vocals
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: false # enable augmentations by audiomentations and pedalboard
+  augmentation_type: null
+  use_mp3_compress: false # Deprecated
+  augmentation_mix: false # Mix several stems of the same type with some probability
+  augmentation_loudness: false # randomly change loudness of each stem
+  augmentation_loudness_type: 1 # Type 1 or 2
+  augmentation_loudness_min: 0
+  augmentation_loudness_max: 0
+  q: 0.95
+  coarse_loss_clip: false
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: true # it's needed for checking on multisong dataset if other is actually instrumental
+  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
+
+inference:
+  batch_size: 4
+  dim_t: 256
+  num_overlap: 2

ckpts/model_ckpt_steps_100000_simplified.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa710fce920b4dae281b0e6cc2acba83345d82ee62d51f7bafeb29636f28f97c
+size 470801253

ckpts/stable_audio_2_0_vae_20hz_official.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2c4a8ec9731594951a27eff4a188a89b82859649c341c51d050101d1ce0b39
+size 624569828

config.json

@@ -0,0 +1,6 @@
+{
+  "is_distilled": false,
+  "model_cfg_path": "src/YingMusicSinger/config/YingMusic_Singer.yaml",
+  "use_ema": true,
+  "vae_config_path": "src/YingMusicSinger/config/stable_audio_2_0_vae_20hz_official.json"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32dc225a6cfff37f2252b7d3b60cbf536f656de349eba6d5b773aa5f5b780e4
+size 2910134776