Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+model_structure.png filter=lfs diff=lfs merge=lfs -text
+teaser.png filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,187 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+### Notice on Third-Party Components
+
+This repository includes a fine-tuned version of the VAE model originally released by Stability AI as part of the **Stable Audio Open** project.  This component is licensed under the [Stability AI Community License](https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE.md), which prohibits redistribution under a different license, including derivative works such as fine-tuned models.
+
+Accordingly, **this specific VAE component is not covered by the Apache License, Version 2.0**, and **may not be used for commercial purposes**.  
+
+Users are advised to consult the original license terms before using this component.
+
+All other code and models in this repository are released under the Apache License, Version 2.0.

README.md

@@ -1,3 +1,37 @@
----
-license: cc-by-4.0
----
+---
+license: apache-2.0
+pipeline_tag: video-to-video
+---
+
+This repository contains the weights of  [ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing](https://arxiv.org/abs/2506.21448).
+
+Project Page: https://thinksound-project.github.io/.
+
+Paper: https://huggingface.co/papers/2506.21448
+
+Github: https://github.com/FunAudioLLM/ThinkSound
+
+<img src="./teaser.png" alt="model_structure" style="zoom:20%;" />
+
+## Abstract
+While end-to-end video-to-audio generation has greatly improved, producing high-fidelity audio that authentically captures the nuances of visual content remains challenging. Like professionals in the creative industries, such generation requires sophisticated reasoning about items such as visual dynamics, acoustic environments, and temporal relationships. We present ThinkSound, a novel framework that leverages Chain-of-Thought (CoT) reasoning to enable stepwise, interactive audio generation and editing for videos. Our approach decomposes the process into three complementary stages: foundational foley generation that creates semantically coherent soundscapes, interactive object-centric refinement through precise user interactions, and targeted editing guided by natural language instructions. At each stage, a multimodal large language model generates contextually aligned CoT reasoning that guides a unified audio foundation model. Furthermore, we introduce AudioCoT, a comprehensive dataset with structured reasoning annotations that establishes connections between visual content, textual descriptions, and sound synthesis. Experiments demonstrate that ThinkSound achieves state-of-the-art performance in video-to-audio generation across both audio metrics and CoT metrics and excels in out-of-distribution Movie Gen Audio benchmark. The demo page is available at https://ThinkSound-Project.github.io.
+
+## Model Overview
+
+<img src="./model_structure.png" alt="model_structure" style="zoom:40%;" />
+
+## Citation
+
+If you find our work useful, please cite our paper: 
+
+```bibtex
+@misc{liu2025thinksoundchainofthoughtreasoningmultimodal,
+    title={ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing}, 
+    author={Huadai Liu and Jialei Wang and Kaicheng Luo and Wen Wang and Qian Chen and Zhou Zhao and Wei Xue},
+    year={2025},
+    eprint={2506.21448},
+    archivePrefix={arXiv},
+    primaryClass={eess.AS},
+    url={https://arxiv.org/abs/2506.21448},   
+}
+```

init_cross_attn.py

@@ -0,0 +1,84 @@
+import torch
+import torch.nn as nn
+from prefigure.prefigure import get_all_args, push_wandb_config
+import json
+import os
+import re
+import torchaudio
+from lightning.pytorch import seed_everything
+import random
+from datetime import datetime
+import numpy as np
+
+from ThinkSound.data.datamodule import DataModule
+from ThinkSound.models import create_model_from_config
+from ThinkSound.models.utils import load_ckpt_state_dict, remove_weight_norm_from_model
+from ThinkSound.inference.sampling import sample, sample_discrete_euler
+from pathlib import Path
+from tqdm import tqdm
+
+def main():
+    args = get_all_args()
+
+    if args.save_dir == '':
+        args.save_dir = args.results_dir
+
+
+    seed = args.seed
+    if os.environ.get("SLURM_PROCID") is not None:
+        seed += int(os.environ.get("SLURM_PROCID"))
+    seed_everything(seed, workers=True)
+
+    # Load config
+    if args.model_config == '':
+        args.model_config = "ThinkSound/configs/model_configs/thinksound.json"
+    with open(args.model_config) as f:
+        model_config = json.load(f)
+
+    duration = float(args.duration_sec)
+    sample_rate = model_config["sample_rate"]
+    latent_length = round(44100 / 64 / 32 * duration)
+
+    model_config["sample_size"] = duration * sample_rate
+    model_config["model"]["diffusion"]["config"]["sync_seq_len"] = 24 * int(duration)
+    model_config["model"]["diffusion"]["config"]["clip_seq_len"] = 8 * int(duration)
+    model_config["model"]["diffusion"]["config"]["latent_seq_len"] = latent_length
+
+    model = create_model_from_config(model_config)
+
+    # model.load_state_dict(torch.load(args.ckpt_dir))
+
+    # Step 2: 加载旧的 checkpoint（不包含cross-attn）
+    old_ckpt = torch.load(args.ckpt_dir, map_location='cpu')
+
+    # Step 3: 仅提取匹配的权重（名字和尺寸都要匹配）
+    model_state = model.state_dict()
+    matched_ckpt = {k: v for k, v in old_ckpt.items() if k in model_state and v.shape == model_state[k].shape}
+    print(f"[INFO] Loaded {len(matched_ckpt)} keys from old checkpoint")
+
+    # Step 4: 加载已有权重
+    model_state.update(matched_ckpt)
+    model.load_state_dict(model_state)
+
+    # Step 5: 初始化 cross-attn 模块（只初始化新增部分）
+    def init_cross_attn_weights(module):
+        if isinstance(module, nn.Linear):
+            nn.init.xavier_uniform_(module.weight)
+            if module.bias is not None:
+                nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.LayerNorm):
+            nn.init.ones_(module.weight)
+            nn.init.zeros_(module.bias)
+
+    # 只遍历 cross-attn 模块进行初始化
+    for name, module in model.named_modules():
+        if 'cross_attn' in name:
+            module.apply(init_cross_attn_weights)
+            print(f"[INIT] Initialized {name}")
+
+    # Step 6: 保存新权重
+    torch.save(model.state_dict(), 'ckpts/thinksound_light_cross_attn.ckpt')
+    print("[DONE] New checkpoint saved with old weights + initialized cross-attn.")
+
+if __name__ == '__main__':
+    main()

synchformer_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aff082f2df5c3bc52759db0c865c7ee772ae6400b860d1b7e90413f2defb67c
+size 950058171

thinksound.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816fa5f73bd8d566e684cef7a8caf2c698f6da100bca561c0c6b4ae244439ebc
+size 21057372552

thinksound_light.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5232db0ca3f1bca319958ea81181267e525228c226f62015d2b0fc624ce1df82
+size 5733246918

thinksound_light_cross_attn.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a80397e1a4f44c9e698ce2b6cbacf5cc775ef598907e41b2241b285b9e7eb78
+size 5909451670

vae.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8132c32ec65bbba2f1457f2659136c5f2cb31f9902af1c659d78c9f7d3aa619e
+size 2521255758