Update model card, assets and license (2026-09-10)

.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
+assets/native_cursor_use_cases.png filter=lfs diff=lfs merge=lfs -text
+assets/x-square-logo.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.

MODEL_VERSION

@@ -0,0 +1 @@
+cont7e3-f2b8ed5

NOTICE

@@ -0,0 +1,23 @@
+X2Streaming-TTS-1.7B
+Copyright (c) 2026 XSquareRobot.
+
+This model release is distributed under the Apache License, Version 2.0.
+See LICENSE for the full terms.
+
+Upstream components
+
+1. Qwen3-TTS-12Hz-1.7B-Base, released by the Qwen team under Apache-2.0:
+   https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base
+   X Square Robot fine-tuned the base checkpoint for the robot_service_v1
+   CustomVoice speaker and supplies the configuration and generation defaults
+   described in README.md. The base model's authors retain their rights in
+   the upstream work.
+
+2. Qwen3-TTS-Tokenizer-12Hz, released by the Qwen team under Apache-2.0:
+   https://huggingface.co/Qwen/Qwen3-TTS-Tokenizer-12Hz
+   The speech tokenizer in speech_tokenizer/ is included unchanged, as
+   identified by the checksums in SHA256SUMS.
+
+The related X2Streaming-TTS method code has its own MIT license:
+https://github.com/X-Square-Robot/X2Streaming-TTS
+That separate code license does not replace the license for these weights.

README.md

@@ -0,0 +1,236 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
+pipeline_tag: text-to-speech
+language:
+  - zh
+  - en
+tags:
+  - qwen3-tts
+  - text-to-speech
+  - streaming
+  - token-level
+  - custom-voice
+  - tensorrt
+  - x2streaming-tts
+  - arxiv:2608.18661
+  - arxiv:2609.09677
+---
+
+<div align="center">
+  <img src="assets/x-square-logo.png" width="140" alt="X Square Robot beaver mascot holding the moon">
+  <h1>X2Streaming-TTS-1.7B</h1>
+  <p><strong>The deployed CustomVoice checkpoint behind X2Streaming-TTS</strong></p>
+  <p>
+    <a href="https://github.com/X-Square-Robot/X2Streaming-TTS"><img src="https://img.shields.io/badge/GitHub-X2Streaming--TTS-black" alt="X2Streaming-TTS"></a>
+    <a href="https://github.com/X-Square-Robot/Qwen3TTS-Streaming"><img src="https://img.shields.io/badge/Engine-Qwen3TTS--Streaming-6f42c1" alt="Qwen3TTS-Streaming"></a>
+    <a href="https://arxiv.org/abs/2608.18661"><img src="https://img.shields.io/badge/arXiv-2608.18661-b31b1b" alt="paper"></a>
+    <a href="https://huggingface.co/x-square-robot/X2-NativeCursor-Qwen3TTS-12Hz"><img src="https://img.shields.io/badge/Hugging%20Face-X2--NativeCursor-yellow" alt="X2-NativeCursor head"></a>
+    <a href="https://arxiv.org/abs/2609.09677"><img src="https://img.shields.io/badge/arXiv-2609.09677-b31b1b" alt="X2-NativeCursor paper"></a>
+  </p>
+</div>
+
+<div align="center">
+  <img src="assets/native_cursor_use_cases.png" width="1000" alt="X2Streaming-TTS and X2-NativeCursor: streaming speech, continuous narration, synchronized highlighting, playback-aware interruption, and dialogue-history updates">
+  <p><em>Speak as text arrives, track reading progress, and use the playback clock to keep interruptions and dialogue history aligned with played audio.</em></p>
+</div>
+
+X2Streaming-TTS-1.7B is a Qwen3-TTS 12 Hz CustomVoice model with one built-in
+Mandarin voice, `robot_service_v1`, fine-tuned by X Square Robot from
+[Qwen3-TTS-12Hz-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base).
+It is the checkpoint served by the
+[Qwen3TTS-Streaming](https://github.com/X-Square-Robot/Qwen3TTS-Streaming) engine in
+X Square Robot's spoken-dialogue stack and the checkpoint the
+[X2Streaming-TTS](https://github.com/X-Square-Robot/X2Streaming-TTS) method and the
+[X2-NativeCursor](https://huggingface.co/x-square-robot/X2-NativeCursor-Qwen3TTS-12Hz)
+progress observer are released against.
+
+The files are in the standard Qwen3-TTS Hugging Face layout, so the checkpoint loads
+with the `qwen_tts` Python package for offline synthesis and exports unchanged through
+the Qwen3TTS-Streaming pipeline for token-level streaming on TensorRT.
+
+## Model details
+
+| | |
+| --- | --- |
+| Architecture | `Qwen3TTSForConditionalGeneration`, 1.7B Talker + Code Predictor, 12 Hz multi-codebook speech tokenizer, Code2Wav decoder |
+| Base model | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
+| Model type | `custom_voice` (built-in speaker table) |
+| Speaker | `robot_service_v1` (speaker id 3000), a Mandarin service-assistant voice |
+| Languages | Mandarin Chinese (primary), English (secondary) |
+| Output | 24 kHz mono waveform |
+| Precision | bfloat16 weights |
+| Release version | `cont7e3-f2b8ed5` (`MODEL_VERSION` file; the engine reports it in its version diagnostics) |
+| License | Apache-2.0 |
+
+## Files
+
+| File | Size | SHA-256 |
+| --- | --: | --- |
+| `model.safetensors` | 3.83 GB | `666b32d4b73e861d39aad1495d95b6fa5dacad186c42d00ff39d52297cf67966` |
+| `config.json` | 4.5 KB | `c9bb0eedce066142902c7c219585189acb559d66cca956f08ca8731581a437c3` |
+| `generation_config.json` | 245 B | `f1b90b4513f3b34c62851049e2492d7b4c5940daf1276f89c82b8ef04127f3aa` |
+| `preprocessor_config.json` | 127 B | `efdde1022ea9d76928bf7a9cd53139138f5ba2e466e837f08f6105ab1af1c119` |
+| `tokenizer_config.json` | 7.3 KB | `dc3c31c3bdaedd5016382bb3cbe07323026775ad51f5a4fb564505992ae4a670` |
+| `vocab.json` | 2.78 MB | `ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910` |
+| `merges.txt` | 1.67 MB | `599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3` |
+| `MODEL_VERSION` | 15 B | `46a822304a74dcb49ce29ed087590c042ea59d57737882394c7d456c3649ef14` |
+| `speech_tokenizer/model.safetensors` | 0.68 GB | `836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258` |
+| `speech_tokenizer/config.json` | 2.3 KB | `ee65bb901c876664ab8707c487157aa1a6ee57c65969b28fb5ec9dc211e68167` |
+| `speech_tokenizer/configuration.json` | 76 B | `6bc26d64eb5024b4d1dab5a52371958b429256d6c9d59787f1f5294a54e0cebd` |
+| `speech_tokenizer/preprocessor_config.json` | 234 B | `fcb3805e597e786d4067706e602f6688524640f8d3396790e2e09b5942fcbdfb` |
+
+`SHA256SUMS` in the repository lists the same digests in `sha256sum` format.
+
+## Quick start
+
+### Download
+
+```bash
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download x-square-robot/X2Streaming-TTS-1.7B \
+  --local-dir ./weights/X2Streaming-TTS-1.7B
+```
+
+### Offline synthesis with `qwen_tts`
+
+Install the official package from [QwenLM/Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS),
+then call `generate_custom_voice` with the built-in speaker:
+
+```python
+import torch
+import soundfile as sf
+from qwen_tts import Qwen3TTSModel
+
+model = Qwen3TTSModel.from_pretrained(
+    "./weights/X2Streaming-TTS-1.7B",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+)
+print(model.get_supported_speakers())   # ['robot_service_v1']
+
+wavs, sr = model.generate_custom_voice(
+    text="您好，我是服务助手，今天的室外温度是二十三摄氏度。",
+    language="Chinese",
+    speaker="robot_service_v1",
+)
+sf.write("output.wav", wavs[0], sr)
+```
+
+`generation_config.json` carries the sampling defaults used in production:
+`temperature 0.9`, `top_k 50`, `top_p 1.0`, `repetition_penalty 1.05`.
+
+### Token-level streaming with Qwen3TTS-Streaming
+
+The engine's `autorun` pipeline exports the checkpoint to ONNX, builds the TensorRT
+engines and starts the service. The `custom-1.7b` variant reads its weights from
+`workspace/models/Qwen3-TTS-12Hz-1.7B-CustomVoice`, so place (or symlink) the
+downloaded directory there and skip the official download:
+
+```bash
+git clone --recursive https://github.com/X-Square-Robot/Qwen3TTS-Streaming.git
+cd Qwen3TTS-Streaming
+mkdir -p workspace/models
+ln -s /path/to/weights/X2Streaming-TTS-1.7B workspace/models/Qwen3-TTS-12Hz-1.7B-CustomVoice
+SKIP_MODELS=1 bash scripts/bash/autorun.sh all -m custom-1.7b --model-release-version cont7e3-f2b8ed5
+```
+
+Once the service is up, `GET /v1/capabilities` lists the exported speaker and the
+supported tasks; the Python and browser SDKs, the native WebSocket protocol and the
+OpenAI Realtime-compatible gateway are documented in the engine's
+[user guide](https://github.com/X-Square-Robot/Qwen3TTS-Streaming/blob/main/docs/user/README.md)
+and [deployment guide](https://github.com/X-Square-Robot/Qwen3TTS-Streaming/blob/main/docs/user/deployment.md).
+
+### With the X2Streaming-TTS method
+
+[X2Streaming-TTS](https://github.com/X-Square-Robot/X2Streaming-TTS) adds causal
+commitment and causal speech-state inheritance on top of the engine through two hook
+patches. Its README walks through applying the patches and running
+`scripts/run_checkpoint_e2e.py` against this checkpoint.
+
+### With the X2-NativeCursor progress observer
+
+[X2-NativeCursor-Qwen3TTS-12Hz](https://huggingface.co/x-square-robot/X2-NativeCursor-Qwen3TTS-12Hz)
+is an 8.2 MB observer head that reads this model's codebook-0 tokens inside the engine
+and publishes a reading cursor into the source text. Its model card explains how to
+enable it (`text_progress.estimator: native`). The [X2-NativeCursor paper](https://arxiv.org/abs/2609.09677)
+describes the observer and its evaluation.
+
+## Training summary
+
+The voice was obtained by fine-tuning Qwen3-TTS-12Hz-1.7B-Base in two stages on an
+internal synthetic Mandarin corpus for a single service-assistant speaker:
+
+| Stage | Data | Epochs | Learning rate | Batch | Precision |
+| --- | --- | --: | --: | --: | --- |
+| 1 | 493 sentence-level utterances from an internal synthetic Mandarin corpus | 8 | 2e-6 | 8 | bf16 |
+| 2 (this release) | the same 493 utterances, continued from stage 1 | 4 | 4e-7 | 8 | bf16 |
+
+The speech tokenizer (`speech_tokenizer/`) is the official Qwen3-TTS-Tokenizer-12Hz,
+included unchanged so that the directory is self-contained.
+
+## Intended use and limitations
+
+- **Intended use.** Mandarin spoken-dialogue and service-assistant applications that
+  need low first-audio latency, in particular token-level streaming from an upstream
+  language model through Qwen3TTS-Streaming.
+- **Single voice.** The checkpoint contains one speaker. Instruction-based style
+  control (`instruct`) is supported by the architecture but was not a training target
+  for this voice.
+- **English.** English text is synthesized, with lower naturalness than Mandarin.
+- **Streaming caveats.** Token-level streaming can still produce hallucinated,
+  repeated or dropped words on some inputs; the rate depends on the text and the
+  segmentation policy. The engine's
+  [known limitations](https://github.com/X-Square-Robot/Qwen3TTS-Streaming/blob/main/docs/user/known_limitations.md)
+  and the X2Streaming-TTS paper describe the failure modes and the mitigations
+  (causal commitment, health-gated state inheritance).
+- **Numbers, dates and units.** Read the text through a text normalizer before
+  synthesis; the X2Streaming-TTS release includes the Chinese normalizer used in the
+  paper. Some date, time and unit formats are misread when passed raw.
+- **Evaluation.** The streaming evaluation protocol and results for the method are in
+  the [paper](https://arxiv.org/abs/2608.18661).
+
+## Citation
+
+```bibtex
+@article{wen2026x2streamingtts,
+  title   = {X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance},
+  author  = {Wen, Rime and Liu, Zehan and Qin, Shawn and Shi, Lights and Gan, Roy and Wang, Hao and Wang, Qian},
+  journal = {arXiv preprint arXiv:2608.18661},
+  year    = {2026},
+}
+```
+
+If you use the X2-NativeCursor progress observer with this checkpoint, also cite:
+
+```bibtex
+@article{liu2026x2nativecursor,
+  title   = {X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS},
+  author  = {Liu, Zehan and Chen, Carl and Wen, Rime and Fu, Kaiqi and Lin, Altman and Qin, Shawn and Shi, Lights and Gan, Roy and Wang, Hao and Wang, Qian},
+  journal = {arXiv preprint arXiv:2609.09677},
+  year    = {2026},
+  url     = {https://arxiv.org/abs/2609.09677},
+}
+```
+
+## License
+
+See [LICENSE](LICENSE) for the full Apache-2.0 terms and [NOTICE](NOTICE) for
+component provenance and attribution.
+
+The weights are released under the Apache License 2.0, Copyright (c) 2026 XSquareRobot.
+They derive from Qwen3-TTS-12Hz-1.7B-Base and include the Qwen3-TTS-Tokenizer-12Hz,
+both released by the Qwen team under Apache-2.0; their notices apply to the
+corresponding components.
+
+## 中文简介
+
+X2Streaming-TTS-1.7B 是 X Square Robot 基于 Qwen3-TTS-12Hz-1.7B-Base 微调的
+CustomVoice 模型，内置一个中文服务助手音色 `robot_service_v1`。它是 Qwen3TTS-Streaming
+引擎在线服务所用的 checkpoint，也是 X2Streaming-TTS 方法与 X2-NativeCursor 进度观察器
+发布时所对应的权重。文件采用 Qwen3-TTS 的标准 Hugging Face 布局：用 `qwen_tts` 包可以
+离线合成，交给 Qwen3TTS-Streaming 的 `autorun` 流水线即可导出 TensorRT 做 token 级流式
+合成。合成前请先做文本正则化（数字、日期、单位）。许可为 Apache-2.0。
+
+论文：[X2Streaming-TTS](https://arxiv.org/abs/2608.18661)；如使用朗读进度观察器，
+请同时引用 [X2-NativeCursor](https://arxiv.org/abs/2609.09677)。

SHA256SUMS

@@ -0,0 +1,12 @@
+c9bb0eedce066142902c7c219585189acb559d66cca956f08ca8731581a437c3  config.json
+f1b90b4513f3b34c62851049e2492d7b4c5940daf1276f89c82b8ef04127f3aa  generation_config.json
+599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3  merges.txt
+efdde1022ea9d76928bf7a9cd53139138f5ba2e466e837f08f6105ab1af1c119  preprocessor_config.json
+dc3c31c3bdaedd5016382bb3cbe07323026775ad51f5a4fb564505992ae4a670  tokenizer_config.json
+ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910  vocab.json
+46a822304a74dcb49ce29ed087590c042ea59d57737882394c7d456c3649ef14  MODEL_VERSION
+666b32d4b73e861d39aad1495d95b6fa5dacad186c42d00ff39d52297cf67966  model.safetensors
+ee65bb901c876664ab8707c487157aa1a6ee57c65969b28fb5ec9dc211e68167  speech_tokenizer/config.json
+6bc26d64eb5024b4d1dab5a52371958b429256d6c9d59787f1f5294a54e0cebd  speech_tokenizer/configuration.json
+836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258  speech_tokenizer/model.safetensors
+fcb3805e597e786d4067706e602f6688524640f8d3396790e2e09b5942fcbdfb  speech_tokenizer/preprocessor_config.json

config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "Qwen3TTSForConditionalGeneration"
+  ],
+  "assistant_token_id": 77091,
+  "im_end_token_id": 151645,
+  "im_start_token_id": 151644,
+  "tts_bos_token_id": 151672,
+  "tts_eos_token_id": 151673,
+  "tts_pad_token_id": 151671,
+  "model_type": "qwen3_tts",
+  "tokenizer_type": "qwen3_tts_tokenizer_12hz",
+  "tts_model_size": "1b7",
+  "tts_model_type": "custom_voice",
+  "speaker_encoder_config": {
+    "enc_dim": 2048,
+    "sample_rate": 24000
+  },
+  "talker_config": {
+    "attention_bias": false,
+    "attention_dropout": 0,
+    "code_predictor_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 3072,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 65536,
+      "max_window_layers": 28,
+      "min_length": 0,
+      "model_type": "qwen3_tts_talker_code_predictor",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_code_groups": 16,
+      "num_hidden_layers": 5,
+      "num_key_value_heads": 8,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": null,
+      "rope_theta": 1000000,
+      "sep_token_id": null,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "dtype": null,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 2048
+    },
+    "codec_bos_id": 2149,
+    "codec_eos_token_id": 2150,
+    "codec_think_id": 2154,
+    "codec_language_id": {
+      "chinese": 2055,
+      "english": 2050,
+      "german": 2053,
+      "italian": 2070,
+      "portuguese": 2071,
+      "spanish": 2054,
+      "japanese": 2058,
+      "korean": 2064,
+      "french": 2061,
+      "russian": 2069
+    },
+    "codec_nothink_id": 2155,
+    "codec_pad_id": 2148,
+    "codec_think_bos_id": 2156,
+    "codec_think_eos_id": 2157,
+    "spk_id": {
+      "robot_service_v1": 3000
+    },
+    "spk_is_dialect": {
+      "robot_service_v1": false
+    },
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 32768,
+    "model_type": "qwen3_tts_talker",
+    "num_attention_heads": 16,
+    "num_code_groups": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "position_id_per_seconds": 13,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "text_hidden_size": 2048,
+    "text_vocab_size": 151936,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 3072
+  },
+  "transformers_version": "4.57.3"
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "repetition_penalty": 1.05,
+  "temperature": 0.9,
+  "top_p": 1.0,
+  "top_k": 50,
+  "subtalker_dosample": true,
+  "subtalker_temperature": 0.9,
+  "subtalker_top_p": 1.0,
+  "subtalker_top_k": 50,
+  "max_new_tokens": 8192
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666b32d4b73e861d39aad1495d95b6fa5dacad186c42d00ff39d52297cf67966
+size 3833402520

preprocessor_config.json

@@ -0,0 +1,6 @@
+{
+  "padding_side": "left",
+  "padding_value": 0.0,
+  "processor_class": "Qwen3TTSProcessor",
+  "return_attention_mask": true
+}

speech_tokenizer/config.json

@@ -0,0 +1,94 @@
+{
+  "architectures": [
+    "Qwen3TTSTokenizerV2Model"
+  ],
+  "model_type": "qwen3_tts_tokenizer_12hz",
+  "encoder_valid_num_quantizers": 16,
+  "input_sample_rate": 24000,
+  "output_sample_rate": 24000,
+  "decode_upsample_rate": 1920,
+  "encode_downsample_rate": 1920,
+  "decoder_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "latent_dim": 1024,
+    "codebook_dim": 512,
+    "codebook_size": 2048,
+    "decoder_dim": 1536,
+    "hidden_act": "silu",
+    "hidden_size": 512,
+    "intermediate_size": 1024,
+    "layer_scale_initial_scale": 0.01,
+    "max_position_embeddings": 8000,
+    "head_dim": 64,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 16,
+    "num_quantizers": 16,
+    "num_semantic_quantizers": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000,
+    "semantic_codebook_size": 4096,
+    "sliding_window": 72,
+    "upsample_rates": [
+      8,
+      5,
+      4,
+      3
+    ],
+    "upsampling_ratios": [
+      2,
+      2
+    ],
+    "vector_quantization_hidden_dimension": 512
+  },
+  "encoder_config": {
+    "_frame_rate": 12.5,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "audio_channels": 1,
+    "codebook_dim": 256,
+    "codebook_size": 2048,
+    "compress": 2,
+    "dilation_growth_rate": 2,
+    "dtype": "float32",
+    "head_dim": 64,
+    "hidden_act": "gelu",
+    "hidden_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "kernel_size": 7,
+    "last_kernel_size": 3,
+    "layer_scale_initial_scale": 0.01,
+    "max_position_embeddings": 8000,
+    "norm_eps": 1e-05,
+    "normalize": false,
+    "num_attention_heads": 8,
+    "num_filters": 64,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 8,
+    "num_quantizers": 32,
+    "num_residual_layers": 1,
+    "num_semantic_quantizers": 1,
+    "pad_mode": "constant",
+    "residual_kernel_size": 3,
+    "rope_theta": 10000.0,
+    "sampling_rate": 24000,
+    "sliding_window": 250,
+    "transformers_version": "4.57.0.dev0",
+    "trim_right_ratio": 1.0,
+    "upsample_groups": 512,
+    "upsampling_ratios": [
+      8,
+      6,
+      5,
+      4
+    ],
+    "use_cache": false,
+    "use_causal_conv": true,
+    "use_conv_shortcut": false,
+    "use_streaming": false,
+    "vector_quantization_hidden_dimension": 256
+  },
+  "transformers_version": "4.57.3"
+}

speech_tokenizer/configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "feature-extraction", "allow_remote": true}

speech_tokenizer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836b7b357f5ea43e889936a3709af68dfe3751881acefe4ecf0dbd30ba571258
+size 682293092

speech_tokenizer/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "chunk_length_s": null,
+  "feature_extractor_type": "EncodecFeatureExtractor",
+  "feature_size": 1,
+  "overlap": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 24000
+}

tokenizer_config.json

@@ -0,0 +1,316 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "extra_special_tokens": {
+    "image_token": "<|image_pad|>",
+    "audio_token": "<|audio_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>",
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>"
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "image_token": "<|image_pad|>",
+  "audio_token": "<|audio_pad|>",
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>",
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>"
+}