Duplicate from HeartMuLa/HeartCodec-oss

Co-authored-by: HeartMuLa <HeartMuLa@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 +1,60 @@
+---
+license: apache-2.0
+language:
+- zh
+- en
+- ja
+- ko
+- es
+pipeline_tag: text-to-audio
+tags:
+- music
+- art
+---
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+- **Developed by:** [HeartMuLa Team]
+- **License:** [Apache 2.0]
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Github Repo:** https://github.com/HeartMuLa/heartlib
+- **Paper:** https://arxiv.org/abs/2601.10547
+- **Demo:** https://heartmula.github.io/
+- **HeartMuLa-oss-3B:** https://huggingface.co/HeartMuLa/HeartMuLa-oss-3B
+- **HeartCodec-oss:** https://huggingface.co/HeartMuLa/HeartCodec-oss
+- **HeartTranscriptor-oss:** https://huggingface.co/HeartMuLa/HeartTranscriptor-oss
+
+
+## Get Started
+
+Check our github repo https://github.com/HeartMuLa/heartlib for a quickstart and local deployment of HeartMuLa.
+
+## Citation
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+If you find HeartMuLa useful, please cite:
+
+```bibtex
+@misc{yang2026heartmulafamilyopensourced,
+      title={HeartMuLa: A Family of Open Sourced Music Foundation Models}, 
+      author={Dongchao Yang and Yuxin Xie and Yuguo Yin and Zheyu Wang and Xiaoyu Yi and Gongxi Zhu and Xiaolong Weng and Zihan Xiong and Yingzhe Ma and Dading Cong and Jingliang Liu and Zihang Huang and Jinghan Ru and Rongjie Huang and Haoran Wan and Peixu Wang and Kuoxi Yu and Helin Wang and Liming Liang and Xianwei Zhuang and Yuanyuan Wang and Haohan Guo and Junjie Cao and Zeqian Ju and Songxiang Liu and Yuewen Cao and Heming Weng and Yuexian Zou},
+      year={2026},
+      eprint={2601.10547},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2601.10547}, 
+}
+```
+
+
+## Contact
+If you are interested in HeartMuLa, feel free to reach us at heartmula.ai@gmail.com

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "HeartCodec"
+  ],
+  "attention_head_dim": 64,
+  "causal": true,
+  "codebook_dim": 32,
+  "codebook_size": 8192,
+  "commitment_weight": 1.0,
+  "decay": 0.9,
+  "default_kernel_size": 7,
+  "delay_kernel_size": 5,
+  "dim": 512,
+  "downsample_factors": [
+    3,
+    4,
+    4,
+    4,
+    5
+  ],
+  "downsample_kernel_sizes": [
+    6,
+    8,
+    8,
+    8,
+    10
+  ],
+  "in_channels": 1024,
+  "init_channel": 64,
+  "latent_hidden_dim": 128,
+  "model_type": "heartcodec",
+  "norm_type": "ada_norm_single",
+  "num_attention_heads": 24,
+  "num_bands": 1,
+  "num_layers": 24,
+  "num_layers_2": 6,
+  "num_quantizers": 8,
+  "num_samples": 2,
+  "out_channels": 256,
+  "res_kernel_size": 7,
+  "sample_rate": 48000,
+  "threshold_ema_dead_code": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "upsample_factors": [
+    5,
+    4,
+    4,
+    4,
+    3
+  ],
+  "upsample_kernel_sizes": [
+    10,
+    8,
+    8,
+    8,
+    6
+  ],
+  "use_cosine_sim": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee7adb88916644d6e639d7ecb9c42cd328556ec8aacc58f0ee4551aee5057d5
+size 6638384012