Duplicate from pymaster/VocalRender

Co-authored-by: Yukun Chen <pymaster@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

LICENSE

@@ -0,0 +1,201 @@
+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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright OpenBMB
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,173 @@
+---
+license: apache-2.0
+base_model: openbmb/VoxCPM2
+pipeline_tag: text-to-speech
+language:
+  - zh
+datasets:
+  - pymaster/CrawlSinger-OS
+tags:
+  - singing-voice-synthesis
+  - score-conditioned
+  - music
+  - arxiv:2607.27768
+---
+
+# VocalRender
+
+**VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition**
+
+- [Paper](https://arxiv.org/abs/2607.27768)
+- [Code and documentation](https://github.com/pymaster17/VocalRender)
+- [Open-source training dataset](https://huggingface.co/datasets/pymaster/CrawlSinger-OS)
+
+VocalRender is a score-native singing voice synthesis (SVS) model designed for
+real-world composition. It synthesizes 48 kHz singing directly from lyrics,
+MIDI pitches, symbolic note values, and tempo through an original combination
+of an interleaved lyric--note representation, continuous acoustic latents, and
+autoregressive diffusion modeling. It does not require phoneme-level
+durations, an explicit duration predictor, or a time-aligned acoustic
+reference.
+
+![VocalRender overview](https://raw.githubusercontent.com/pymaster17/VocalRender/main/assets/intro.png)
+
+## How it works
+
+VocalRender combines three components:
+
+1. A score-native interleaved representation serializes BPM followed by each
+   lyric syllable and its associated `(pitch, note-value)` pairs. This retains
+   lyric-to-note alignment and supports melisma.
+2. An Audio VAE represents singing as compact continuous acoustic latents.
+3. An autoregressive diffusion model generates the latent sequence patch by
+   patch and decides when to stop. The VAE decoder renders the result as a
+   waveform.
+
+![VocalRender architecture](https://raw.githubusercontent.com/pymaster17/VocalRender/main/assets/structure.png)
+
+## Checkpoints
+
+This repository contains two variants with the **same architecture, parameter
+count, and speech-pretrained base-model initialization**. Their only
+difference is the training recipe (training corpus and schedule):
+
+| Variant | Repository path | Training data and strategy | Paper results |
+| --- | --- | --- | --- |
+| **VocalRender** | `VocalRender/` | CrawlSinger-OS (>2,300 h); 40k-step synthetic pretraining followed by 20k-step real-data finetuning | Stronger subjective score following (MS-MOS 2.96) |
+| **VocalRender-Pro** | `VocalRender-Pro/` | CrawlSinger (>5,600 h of in-house real singing); 160k training steps | Better intelligibility, speaker similarity, naturalness, and OOD robustness; MS-MOS 2.71 |
+
+VocalRender-Pro reduces WER from 4.44 to 3.88 and improves speaker similarity
+from 0.922 to 0.929 on Opencpop. On CrawlSinger-Eval, WER changes from 4.52 to
+4.45 and similarity from 0.919 to 0.926. The paper relates these improvements
+to the larger amount of real singing and broader singer coverage. VocalRender's
+higher score-following score may reflect more reliable score annotations in
+its real-data finetuning subset.
+
+Each directory contains the model weights, AudioVAE, model configuration, and
+extended SVS tokenizer required by the inference code. Both checkpoints have
+the same model size; each is approximately 9.5 GB to download.
+
+## Installation
+
+```bash
+git clone --recurse-submodules https://github.com/pymaster17/VocalRender.git
+cd VocalRender
+uv sync
+source .venv/bin/activate
+```
+
+## Download
+
+Download either checkpoint into the repository's `pretrained_models/`
+directory:
+
+```bash
+# VocalRender
+hf download pymaster/VocalRender \
+    --include "VocalRender/*" \
+    --local-dir pretrained_models
+
+# Or VocalRender-Pro
+hf download pymaster/VocalRender \
+    --include "VocalRender-Pro/*" \
+    --local-dir pretrained_models
+```
+
+## Quick inference
+
+The GitHub repository includes three ready-to-use prompt/score pairs selected
+from OpenCpop. This command runs the first demo:
+
+```bash
+python scripts/infer_vocalrender_svs_single.py \
+    --ckpt_dir pretrained_models/VocalRender \
+    --json_file examples/opencpop_demo.json \
+    --item_name 2003000087 \
+    --prompt_audio examples/prompt_audio/2003000081.wav \
+    --output demo_2003000087.wav
+```
+
+Additional bundled pairs are `2017000646` with prompt `2017000644.wav`, and
+`2044001652` with prompt `2044001666.wav`. The prompt clips are 4.19-6.17
+seconds long and do not overlap their paired target segment. Clone the
+[GitHub repository](https://github.com/pymaster17/VocalRender) to obtain the
+scripts and examples. The excerpts remain subject to the
+[OpenCpop](https://wenet.org.cn/opencpop/) terms.
+
+Use `pretrained_models/VocalRender-Pro` as `--ckpt_dir` to run the Pro model.
+Full generation requires a CUDA-capable compute node. Prompt audio is required:
+the released checkpoints were trained with prompt audio on every sample
+(`prompt_audio_prob=1.0`), so prompt-free inference is unsupported and may
+substantially degrade quality. Use a clean 2-8 second singing clip, which also
+provides the target timbre. See the
+[repository README](https://github.com/pymaster17/VocalRender#batch-inference) for
+batch-inference options.
+
+## Input format
+
+```json
+{
+  "item_name": "demo",
+  "word": ["我", "的", "孤", "独"],
+  "pitch": [65, 64, 64, 65, 67, 65],
+  "note": ["<NOTE_8>", "<NOTE_32>", "<NOTE_16>", "<NOTE_16>", "<NOTE_16>", "<NOTE_8>"],
+  "pitch2word": [0, 1, 2, 2, 2, 3],
+  "bpm": 64
+}
+```
+
+`pitch2word[i]` identifies the lyric index associated with note `i`, allowing
+one lyric syllable to span multiple notes. `word_dur` and `pitch_dur` are
+optional fields used only for visualization and evaluation; they are not model
+inputs.
+
+## Limitations
+
+- The released checkpoints primarily target Mandarin Chinese singing.
+- Checkpoint loading and generation require substantial disk space, system
+  memory, and GPU memory.
+- Output quality depends on the musical validity and lyric-to-note alignment of
+  the input score.
+
+## Model foundation
+
+The released implementation initializes its ARDM backbone from the
+speech-pretrained [VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) weights.
+The score-native representation, SVS formulation, data pipeline, and singing
+training recipe are introduced by VocalRender.
+
+## Citation
+
+```bibtex
+@article{chen2026vocalrender,
+  title   = {VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition},
+  author  = {Chen, Yukun and Wang, Tianrui and Mu, Zhaoxi and Yang, Xinyu and Chng, EngSiong},
+  journal = {arXiv preprint arXiv:2607.27768},
+  year    = {2026},
+  url     = {https://arxiv.org/abs/2607.27768}
+}
+```
+
+## License
+
+Apache License 2.0. See the repository's `LICENSE` file for details.

VocalRender-Pro/audiovae.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b5d51e107e0507d4acc976cfdadb64edd6fd06d1f751dadbf2fd1594274bf1
+size 376951122

VocalRender-Pro/chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

VocalRender-Pro/config.json

@@ -0,0 +1,67 @@
+{
+    "architecture": "voxcpm2",
+    "lm_config": {
+        "bos_token_id": 1,
+        "eos_token_id": 2,
+        "hidden_size": 2048,
+        "intermediate_size": 6144,
+        "max_position_embeddings": 32768,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 28,
+        "num_key_value_heads": 2,
+        "rms_norm_eps": 1e-05,
+        "rope_theta": 10000,
+        "kv_channels": 128,
+        "rope_scaling": {
+            "type": "longrope", 
+            "long_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
+            "short_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
+            "original_max_position_embeddings": 32768
+        },    
+        "vocab_size": 73448,
+        "use_mup": false,
+        "scale_emb": 12,
+        "dim_model_base": 256,
+        "scale_depth": 1.4
+    },
+    "patch_size": 4,
+    "feat_dim": 64,
+    "scalar_quantization_latent_dim": 512,
+    "scalar_quantization_scale": 9,
+    "residual_lm_num_layers": 8,
+    "residual_lm_no_rope": true,
+    "encoder_config": {
+        "hidden_dim": 1024,
+        "ffn_dim": 4096,
+        "num_heads": 16,
+        "num_layers": 12,
+        "kv_channels": 128
+    },
+    "dit_config": {
+        "hidden_dim": 1024,
+        "ffn_dim": 4096,
+        "num_heads": 16,
+        "num_layers": 12,
+        "kv_channels": 128,
+        "mean_mode": false,
+        "cfm_config": {
+            "sigma_min": 1e-06,
+            "solver": "euler",
+            "t_scheduler": "log-norm",
+            "inference_cfg_rate": 2.0
+        }
+    },
+    "audio_vae_config": {
+        "encoder_dim": 128,
+        "encoder_rates": [2, 5, 8, 8],
+        "latent_dim": 64,
+        "decoder_dim": 2048,
+        "decoder_rates": [8, 6, 5, 2, 2, 2],
+        "sr_bin_boundaries": [20000, 30000, 40000],
+        "sample_rate": 16000,
+        "out_sample_rate": 48000
+    },
+    "max_length": 8192,
+    "device": "cuda",
+    "dtype": "bfloat16"
+}

VocalRender-Pro/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d790784ec77a3f8f61c7e0e066e957dc04c95a22697990cc6c3f05d5dfb2c716
+size 9163382376

VocalRender-Pro/tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

VocalRender/audiovae.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b5d51e107e0507d4acc976cfdadb64edd6fd06d1f751dadbf2fd1594274bf1
+size 376951122

VocalRender/chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

VocalRender/config.json

@@ -0,0 +1,67 @@
+{
+    "architecture": "voxcpm2",
+    "lm_config": {
+        "bos_token_id": 1,
+        "eos_token_id": 2,
+        "hidden_size": 2048,
+        "intermediate_size": 6144,
+        "max_position_embeddings": 32768,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 28,
+        "num_key_value_heads": 2,
+        "rms_norm_eps": 1e-05,
+        "rope_theta": 10000,
+        "kv_channels": 128,
+        "rope_scaling": {
+            "type": "longrope", 
+            "long_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
+            "short_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
+            "original_max_position_embeddings": 32768
+        },    
+        "vocab_size": 73448,
+        "use_mup": false,
+        "scale_emb": 12,
+        "dim_model_base": 256,
+        "scale_depth": 1.4
+    },
+    "patch_size": 4,
+    "feat_dim": 64,
+    "scalar_quantization_latent_dim": 512,
+    "scalar_quantization_scale": 9,
+    "residual_lm_num_layers": 8,
+    "residual_lm_no_rope": true,
+    "encoder_config": {
+        "hidden_dim": 1024,
+        "ffn_dim": 4096,
+        "num_heads": 16,
+        "num_layers": 12,
+        "kv_channels": 128
+    },
+    "dit_config": {
+        "hidden_dim": 1024,
+        "ffn_dim": 4096,
+        "num_heads": 16,
+        "num_layers": 12,
+        "kv_channels": 128,
+        "mean_mode": false,
+        "cfm_config": {
+            "sigma_min": 1e-06,
+            "solver": "euler",
+            "t_scheduler": "log-norm",
+            "inference_cfg_rate": 2.0
+        }
+    },
+    "audio_vae_config": {
+        "encoder_dim": 128,
+        "encoder_rates": [2, 5, 8, 8],
+        "latent_dim": 64,
+        "decoder_dim": 2048,
+        "decoder_rates": [8, 6, 5, 2, 2, 2],
+        "sr_bin_boundaries": [20000, 30000, 40000],
+        "sample_rate": 16000,
+        "out_sample_rate": 48000
+    },
+    "max_length": 8192,
+    "device": "cuda",
+    "dtype": "bfloat16"
+}

VocalRender/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44370632ef6ada8910e8b84d5470a1d00d71d50c209f48f2664813a8fea48576
+size 9163382376

VocalRender/tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}