Duplicate from CypressYang/SongBloom

Co-authored-by: CypressYang <CypressYang@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 +1,17 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+library_name: songbloom
+---
+
+## Introduction
+We propose SongBloom, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms.
+
+## Model Configuration
+TODO
+
+## Papers
+* [Model Paper](https://huggingface.co/papers/2506.07634)
+* [Github Repo](https://github.com/Cypress-Yang/SongBloom)

autoencoder_music_dsp1920.ckpt

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

songbloom_full_150s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeaee1dc889c8790e53064189ddcb7c66396cbfef3b15794a53e41d17d55fd2
+size 7827256017

songbloom_full_150s.yaml

@@ -0,0 +1,76 @@
+cfg_file: 
+precision: 'bf16-mixed' # ['16-mixed', 'bf16-mixed']
+min_dur: 60
+max_dur: 150
+sr: 48000
+
+pretrained_path: ${dynamic_path:???/songbloom_full_150s.pt}
+continue_checkpoint: 
+
+train_dataset:
+  lyric_processor: phoneme
+  prompt_len: 10
+
+vae:
+  vae_cfg: ${dynamic_path:???/stable_audio_1920_vae.json}
+  vae_ckpt: ${dynamic_path:???/autoencoder_music_dsp1920.ckpt}
+  sr: ${sr}
+
+model: 
+  block_size: 16 
+  latent_dim: 64
+  dim: 1536
+  num_heads: 24
+  lm_layers: 36
+  diff_layers: 12
+  num_pitch: 16384
+  time_cond_type: prepend 
+  timestep_features_dim: 256
+  diffusion_objective: rectified_flow
+  timestep_sampler: logit_normal
+  backend: llama
+  rotary_base_val: 20000
+  init_std: 0.02
+  h_dropout: 0.05 
+
+  condition_provider_cfg:
+    prompt_wav:
+      type: audio_tokenizer_wrapper
+      output_dim: ${model.dim}
+      audio_tokenizer: 
+      max_len: 250 # 25.0 * 10s
+    lyrics:
+      type: phoneme_tokenizer
+      output_dim: ${model.dim}
+      vocab_list: ${load_yaml:${dynamic_path:???/vocab_g2p.yaml}}
+      max_len: 600
+      max_sentence_per_structure: 50
+      mode: sum
+
+
+  cfg_dropout: 0.1
+  attribute_dropout:
+    text:
+      lyrics: 0.
+    wav:
+      prompt_wav: 0.1
+
+  fuser_cfg:
+    cross_attention_pos_emb: false
+    cross_attention_pos_emb_scale: 1
+    sum: []
+    prepend: [lyrics, prompt_wav] 
+    cross: []      
+    input_interpolate: []
+
+
+
+inference:
+  cfg_coef: 1.5 
+  temp: 0.9
+  diff_temp: 0.95
+  top_k: 100
+  penalty_repeat: True
+  penalty_window: 50
+  steps: 36
+  dit_cfg_type: h

songbloom_full_150s_dpo.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734a5f2700ca8fb660d8a904ba513610aef3a46cf6f10e4db365e02df7e31758
+size 7258793371

songbloom_full_150s_dpo.yaml

@@ -0,0 +1,76 @@
+cfg_file: 
+precision: 'bf16-mixed' # ['16-mixed', 'bf16-mixed']
+min_dur: 60
+max_dur: 150
+sr: 48000
+
+pretrained_path: ${dynamic_path:???/songbloom_full_150s_dpo.pt}
+continue_checkpoint: 
+
+train_dataset:
+  lyric_processor: phoneme
+  prompt_len: 10
+
+vae:
+  vae_cfg: ${dynamic_path:???/stable_audio_1920_vae.json}
+  vae_ckpt: ${dynamic_path:???/autoencoder_music_dsp1920.ckpt}
+  sr: ${sr}
+
+model: 
+  block_size: 16 
+  latent_dim: 64
+  dim: 1536
+  num_heads: 24
+  lm_layers: 36
+  diff_layers: 12
+  num_pitch: 16384
+  time_cond_type: prepend 
+  timestep_features_dim: 256
+  diffusion_objective: rectified_flow
+  timestep_sampler: logit_normal
+  backend: llama
+  rotary_base_val: 20000
+  init_std: 0.02
+  h_dropout: 0.05 
+
+  condition_provider_cfg:
+    prompt_wav:
+      type: audio_tokenizer_wrapper
+      output_dim: ${model.dim}
+      audio_tokenizer: 
+      max_len: 250 # 25.0 * 10s
+    lyrics:
+      type: phoneme_tokenizer
+      output_dim: ${model.dim}
+      vocab_list: ${load_yaml:${dynamic_path:???/vocab_g2p.yaml}}
+      max_len: 600
+      max_sentence_per_structure: 50
+      mode: sum
+
+
+  cfg_dropout: 0.1
+  attribute_dropout:
+    text:
+      lyrics: 0.
+    wav:
+      prompt_wav: 0.1
+
+  fuser_cfg:
+    cross_attention_pos_emb: false
+    cross_attention_pos_emb_scale: 1
+    sum: []
+    prepend: [lyrics, prompt_wav] 
+    cross: []      
+    input_interpolate: []
+
+
+
+inference:
+  cfg_coef: 1.5 
+  temp: 0.9
+  diff_temp: 0.95
+  top_k: 100
+  penalty_repeat: True
+  penalty_window: 50
+  steps: 36
+  dit_cfg_type: h

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
+        }
+    }
+}

vocab_g2p.yaml

@@ -0,0 +1,330 @@
+- ''
+- '[verse]'
+- '[chorus]'
+- '[bridge]'
+- '[intro]'
+- '[outro]'
+- '[inst]'
+- '[silence]'
+- '!'
+- ','
+- '-'
+- .
+- '?'
+- AA
+- AA0
+- AA1
+- AA2
+- AE0
+- AE1
+- AE2
+- AH0
+- AH1
+- AH2
+- AO0
+- AO1
+- AO2
+- AW0
+- AW1
+- AW2
+- AY0
+- AY1
+- AY2
+- B
+- CH
+- D
+- DH
+- E1
+- E2
+- E3
+- E4
+- E5
+- EE
+- EH0
+- EH1
+- EH2
+- ER
+- ER0
+- ER1
+- ER2
+- EY0
+- EY1
+- EY2
+- En1
+- En2
+- En3
+- En4
+- En5
+- F
+- G
+- HH
+- I
+- IH
+- IH0
+- IH1
+- IH2
+- IY0
+- IY1
+- IY2
+- JH
+- K
+- L
+- M
+- N
+- NG
+- OO
+- OW0
+- OW1
+- OW2
+- OY0
+- OY1
+- OY2
+- P
+- R
+- S
+- SH
+- SP
+- SP2
+- SP3
+- T
+- TH
+- U
+- UH0
+- UH1
+- UH2
+- UNK
+- UW0
+- UW1
+- UW2
+- V
+- W
+- Y
+- Z
+- ZH
+- _
+- a
+- a1
+- a2
+- a3
+- a4
+- a5
+- ai1
+- ai2
+- ai3
+- ai4
+- ai5
+- an1
+- an2
+- an3
+- an4
+- an5
+- ang1
+- ang2
+- ang3
+- ang4
+- ang5
+- ao1
+- ao2
+- ao3
+- ao4
+- ao5
+- b
+- by
+- c
+- ch
+- cl
+- d
+- dy
+- e
+- e1
+- e2
+- e3
+- e4
+- e5
+- ei1
+- ei2
+- ei3
+- ei4
+- ei5
+- en1
+- en2
+- en3
+- en4
+- en5
+- eng1
+- eng2
+- eng3
+- eng4
+- eng5
+- er1
+- er2
+- er3
+- er4
+- er5
+- f
+- g
+- gy
+- h
+- hy
+- i
+- i01
+- i02
+- i03
+- i04
+- i05
+- i1
+- i2
+- i3
+- i4
+- i5
+- ia1
+- ia2
+- ia3
+- ia4
+- ia5
+- ian1
+- ian2
+- ian3
+- ian4
+- ian5
+- iang1
+- iang2
+- iang3
+- iang4
+- iang5
+- iao1
+- iao2
+- iao3
+- iao4
+- iao5
+- ie1
+- ie2
+- ie3
+- ie4
+- ie5
+- in1
+- in2
+- in3
+- in4
+- in5
+- ing1
+- ing2
+- ing3
+- ing4
+- ing5
+- iong1
+- iong2
+- iong3
+- iong4
+- iong5
+- ir1
+- ir2
+- ir3
+- ir4
+- ir5
+- iu1
+- iu2
+- iu3
+- iu4
+- iu5
+- j
+- k
+- ky
+- l
+- m
+- my
+- n
+- ny
+- o
+- o1
+- o2
+- o3
+- o4
+- o5
+- ong1
+- ong2
+- ong3
+- ong4
+- ong5
+- ou1
+- ou2
+- ou3
+- ou4
+- ou5
+- p
+- py
+- q
+- r
+- ry
+- s
+- sh
+- t
+- ts
+- u
+- u1
+- u2
+- u3
+- u4
+- u5
+- ua1
+- ua2
+- ua3
+- ua4
+- ua5
+- uai1
+- uai2
+- uai3
+- uai4
+- uai5
+- uan1
+- uan2
+- uan3
+- uan4
+- uan5
+- uang1
+- uang2
+- uang3
+- uang4
+- uang5
+- ui1
+- ui2
+- ui3
+- ui4
+- ui5
+- un1
+- un2
+- un3
+- un4
+- un5
+- uo1
+- uo2
+- uo3
+- uo4
+- uo5
+- v
+- v1
+- v2
+- v3
+- v4
+- v5
+- van1
+- van2
+- van3
+- van4
+- van5
+- ve1
+- ve2
+- ve3
+- ve4
+- ve5
+- vn1
+- vn2
+- vn3
+- vn4
+- vn5
+- w
+- x
+- y
+- z
+- zh
+- "\u2026"