Duplicate from GiantAILab/YingMusic-Singer

Co-authored-by: RICHARD CHEN <RICHARD12369@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 +1,11 @@
+---
+license: cc-by-nc-4.0
+---
+# YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance
+
+github:[YingMusic-Singer](https://github.com/GiantAILab/YingMusic-Singer)
+
+## Short Intro
+
+YingMusic-Singer is a unified framework for Zero-shot Singing Voice Synthesis (SVS) and Editing, driven by Annotation-free Melody Guidance. Addressing the scalability challenges of real-world applications, our system eliminates the reliance on costly phoneme-level alignment and manual melody annotations. It enables arbitrary lyrics to be synthesized or edited with any reference melody in a zero-shot manner.
+Our approach leverages a Diffusion Transformer (DiT) based generative model, incorporating a pre-trained melody extraction module to derive MIDI information directly from reference audio. By introducing a structured guidance mechanism and employing Flow-GRPO reinforcement learning, we achieve superior pronunciation clarity, melodic accuracy, and musicality without requiring fine-grained alignment.

autoencoder_music_dsp1920.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ccb6c83613781ad32e998a90597ba7eb9292911a224598da1fd53728eb4cd3
+size 674920616

beta/yingsinger.dev.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a420c558f513863a526a38ade7eacd0c6bf770deed8cd5e3a4bb8a61780f5d0
+size 1820018079

rmvpe.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dc1809cf4cdb0a18db93441816bc327e14e5644b72eeaae5220560c6736fe2
+size 368492925

singer.v1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7f2e939af6e1bac06e1f14bf1e9a66628eb748c3a62420213983f6c08fe3a1
+size 1316346039

some.pt

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

stable_audio_1920_vae.json

@@ -0,0 +1,122 @@
+{
+    "model_type": "autoencoder",
+    "sample_size": 403200,
+    "sample_rate": 48000,
+    "audio_channels": 2,
+    "model": {
+        "encoder": {
+            "type": "oobleck",
+            "config": {
+                "in_channels": 2,
+                "channels": 128,
+                "c_mults": [1, 2, 4, 8, 16],
+                "strides": [2, 4, 4, 6, 10],
+                "latent_dim": 128,
+                "use_snake": true
+            }
+        },
+        "decoder": {
+            "type": "oobleck",
+            "config": {
+                "out_channels": 2,
+                "channels": 128,
+                "c_mults": [1, 2, 4, 8, 16],
+                "strides": [2, 4, 4, 6, 10],
+                "latent_dim": 64,
+                "use_snake": true,
+                "final_tanh": false
+            }
+        },
+        "bottleneck": {
+            "type": "vae"
+        },
+        "latent_dim": 64,
+        "downsampling_ratio": 1920,
+        "io_channels": 2
+    },
+    "training": {
+        "learning_rate": 1.5e-4,
+        "warmup_steps": 0,
+        "use_ema": true,
+        "optimizer_configs": {
+            "autoencoder": {
+                "optimizer": {
+                    "type": "AdamW",
+                    "config": {
+                        "betas": [0.8, 0.99],
+                        "lr": 1.5e-4,
+                        "weight_decay": 1e-3
+                    }
+                },
+                "scheduler": {
+                    "type": "InverseLR",
+                    "config": {
+                        "inv_gamma": 200000,
+                        "power": 0.5,
+                        "warmup": 0.999
+                    }
+                }
+            },
+            "discriminator": {
+                "optimizer": {
+                    "type": "AdamW",
+                    "config": {
+                        "betas": [0.8, 0.99],
+                        "lr": 3e-4,
+                        "weight_decay": 1e-3
+                    }
+                },
+                "scheduler": {
+                    "type": "InverseLR",
+                    "config": {
+                        "inv_gamma": 200000,
+                        "power": 0.5,
+                        "warmup": 0.999
+                    }
+                }
+            }
+        },
+        "loss_configs": {
+            "discriminator": {
+                "type": "encodec",
+                "config": {
+                    "filters": 64,
+                    "n_ffts": [2048, 1024, 512, 256, 128],
+                    "hop_lengths": [512, 256, 128, 64, 32],
+                    "win_lengths": [2048, 1024, 512, 256, 128]
+                },
+                "weights": {
+                    "adversarial": 0.1,
+                    "feature_matching": 5.0
+                }
+            },
+            "spectral": {
+                "type": "mrstft",
+                "config": {
+                    "fft_sizes": [2048, 1024, 512, 256, 128, 64, 32],
+                    "hop_sizes": [512, 256, 128, 64, 32, 16, 8],
+                    "win_lengths": [2048, 1024, 512, 256, 128, 64, 32],
+                    "perceptual_weighting": true
+                },
+                "weights": {
+                    "mrstft": 1.0
+                }
+            },
+            "time": {
+                "type": "l1",
+                "weights": {
+                    "l1": 0.0
+                }
+            },
+            "bottleneck": {
+                "type": "kl",
+                "weights": {
+                    "kl": 1e-4
+                }
+            }
+        },
+        "demo": {
+            "demo_every": 2000
+        }
+    }
+}