Mirror AutoDroid pins from Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4@818569c6b832

.gitattributes

@@ -33,3 +33,7 @@ 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
+codec_decoder_fp16.onnx.data filter=lfs diff=lfs merge=lfs -text
+fast_ar_int4.onnx.data filter=lfs diff=lfs merge=lfs -text
+slow_ar_int4.onnx.data filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

AUTODROID_MIRROR.md

@@ -0,0 +1,7 @@
+# AutoDroid artifact mirror
+
+This repository preserves selected, unmodified files from `Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4` at commit `818569c6b832118ad68d61bbd873abe250fcd68a`.
+
+Original authorship, licenses, and notices remain applicable. This is an independent availability mirror and does not imply upstream endorsement.
+
+See `AUTODROID_SOURCE.json` for original paths, byte sizes, and SHA-256 digests. Only files required by AutoDroid and upstream documentation are included; this is not a complete training or Transformers checkpoint.

AUTODROID_SOURCE.json

@@ -0,0 +1,95 @@
+{
+  "sourceRepository": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+  "sourceRevision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+  "purpose": "Unmodified pinned artifacts used by AutoDroid",
+  "licenseReview": {
+    "sourceRevision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+    "declaredLicense": "apache-2.0",
+    "evidence": "https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4/blob/818569c6b832118ad68d61bbd873abe250fcd68a/README.md",
+    "status": "approved",
+    "reason": "Pinned upstream card permits redistribution. Preserve upstream cards and notices, original authorship, and the applicable license texts; artifact bytes are unmodified.",
+    "additionalFiles": [
+      {
+        "localPath": "tools/hf_mirror/licenses/Apache-2.0.txt",
+        "pathInRepo": "licenses/Apache-2.0.txt",
+        "source": "https://www.apache.org/licenses/LICENSE-2.0.txt",
+        "sha256": "c98068a3b6a564e4c70ab7c2ee2c980725987908909e99915759efa28ac7b533"
+      },
+      {
+        "localPath": "tools/hf_mirror/licenses/Audio8-NOTICE.txt",
+        "pathInRepo": "licenses/Audio8-NOTICE.txt",
+        "source": "https://raw.githubusercontent.com/Audio8-AI/Audio8_TTS/master/NOTICE",
+        "sha256": "819129644b28fb066221d782dd27a6fe1d35f33f46718d4e61570614fb38854e"
+      }
+    ]
+  },
+  "artifacts": [
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "codec_decoder_fp16.onnx",
+      "sizeBytes": 594319,
+      "sha256": "6e379be31db6c1b0c111e0e3d2aeb10717ee96b197462b926de411e75a1fd019",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:163"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "codec_decoder_fp16.onnx.data",
+      "sizeBytes": 260741440,
+      "sha256": "18838f686aa7c1528fb69ec11e1ab404fdc4dc823d13219abfd4b327988527c0",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:168"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "fast_ar_int4.onnx",
+      "sizeBytes": 156318,
+      "sha256": "808c5a0c95c28d90337d925a9a8f6075f7ff8eb7b3080d2b34c4133479a6dc94",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:153"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "fast_ar_int4.onnx.data",
+      "sizeBytes": 35055104,
+      "sha256": "183be0c9f26b27c605b92a0875beb93f8f98b771f27f65cab133c73610868325",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:158"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "runtime_manifest.json",
+      "sizeBytes": 1080,
+      "sha256": "6473ae7d0106a2e369e442c72a71d2d46d8fbd3fe18c80d80b1b46e4aa241930",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:133"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "slow_ar_int4.onnx",
+      "sizeBytes": 900218,
+      "sha256": "0cf7701d6da81f888b49ba6e752445d9786a9915ba30dcf084f7743bdda96834",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:143"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "slow_ar_int4.onnx.data",
+      "sizeBytes": 290267090,
+      "sha256": "bb217f654039692204386b7e5b74d98e9268863bb664a849aa123a9053d6c824",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:148"
+    },
+    {
+      "repo": "Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4",
+      "revision": "818569c6b832118ad68d61bbd873abe250fcd68a",
+      "filename": "tokenizer/tokenizer.json",
+      "sizeBytes": 12217872,
+      "sha256": "f24e08099d45a8adf3f52f5f0b03276e433bb9d689bb15fcbcc48ce58744588b",
+      "source": "app/src/main/java/com/example/autodroid/data/voice/model/VoiceModelCatalog.kt:138"
+    }
+  ],
+  "preservedDocuments": [
+    "README.md"
+  ]
+}

README.md

@@ -0,0 +1,241 @@
+---
+license: apache-2.0
+language:
+  - yue
+  - zh
+  - nl
+  - en
+  - fr
+  - de
+  - it
+  - ja
+  - ko
+  - pl
+  - es
+library_name: onnxruntime
+pipeline_tag: text-to-speech
+base_model: Audio8/Audio8-TTS-Preview-0.6b
+tags:
+  - onnx
+  - int4
+  - audio
+  - text-to-speech
+  - tts
+  - voice-cloning
+  - zero-shot
+  - multilingual
+---
+
+<div align="center">
+
+<img src="./20260729-124515.jpeg" alt="Audio8" width="760">
+
+<h1>&nbsp;&nbsp;Audio8 TTS Preview 0.6B ONNX INT4</h1>
+
+**SOTA-class multilingual TTS at compact scale, packaged for low-resource CPU inference.**
+
+[![GitHub](https://img.shields.io/badge/GitHub-Audio8__TTS-black?style=for-the-badge&logo=github)](https://github.com/Audio8-AI/Audio8_TTS)
+[![Base Model](https://img.shields.io/badge/%F0%9F%A4%97%20Base%20Model-0.6B-FFD21E?style=for-the-badge)](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b)
+[![Demo](https://img.shields.io/badge/Live-Demo-brightgreen?style=for-the-badge&logo=githubpages)](https://audio8-ai.github.io/Audio8_TTS/)
+[![ONNX Runtime](https://img.shields.io/badge/ONNX-Runtime-005CED?style=for-the-badge&logo=onnx)](https://onnxruntime.ai/)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue?style=for-the-badge)](https://github.com/Audio8-AI/Audio8_TTS/blob/master/LICENSE)
+
+</div>
+
+Audio8 TTS Preview is a 0.6B-parameter multilingual text-to-speech model with
+zero-shot voice cloning. This repository provides its CPU-oriented ONNX
+deployment: weight-only INT4 DualAR models, an FP16 neural audio codec, the
+tokenizer, and the optional FP16 encoder used to register reference voices.
+
+> **Model files only.** Inference, streaming service, and voice-registration
+> code live in the
+> [Audio8 TTS repository](https://github.com/Audio8-AI/Audio8_TTS/tree/master/onnx_runtime).
+
+## Why this ONNX release
+
+| | Deployment characteristic |
+|---|---|
+| **CPU native** | ONNX Runtime `CPUExecutionProvider`; no CUDA requirement |
+| **Small runtime** | No PyTorch, Transformers, or Hugging Face Hub dependency after download |
+| **Low memory** | About 1 GiB after loading in the tested Apple M2 configuration |
+| **Voice cloning** | Bundled FP16 codec encoder for reusable local voice profiles |
+| **Local service** | CLI, web UI, HTTP API, streaming PCM, and OpenAI-compatible endpoint |
+
+### Precision and footprint
+
+| Component | Precision |
+|---|---|
+| Slow/Fast AR weights | Weight-only INT4 |
+| Activations, hidden states, and KV cache | FP16 |
+| Codec encoder and decoder | FP16 |
+| Waveform output | FP32, 44.1 kHz mono |
+
+Normal synthesis loads only the Slow AR, Fast AR, and codec decoder sessions.
+On a 16 GB Apple M2 MacBook Air with five ONNX Runtime threads, the service
+used about **1004 MiB after loading** and approximately **1.1-1.2 GiB at
+synthesis peak**. Voice registration releases the online sessions before
+loading the codec encoder; the measured registration peak was approximately
+**1.55 GiB**. Actual memory use varies by platform and allocator behavior.
+
+The online model files occupy about **572 MiB**. The complete repository,
+including the optional voice-registration encoder, is about **968 MiB**.
+
+## Supported Languages
+
+<p align="center">
+  <strong>Cantonese</strong> &nbsp;·&nbsp;
+  <strong>Chinese</strong> &nbsp;·&nbsp;
+  <strong>Dutch</strong> &nbsp;·&nbsp;
+  <strong>English</strong><br>
+  <strong>French</strong> &nbsp;·&nbsp;
+  <strong>German</strong> &nbsp;·&nbsp;
+  <strong>Italian</strong> &nbsp;·&nbsp;
+  <strong>Japanese</strong><br>
+  <strong>Korean</strong> &nbsp;·&nbsp;
+  <strong>Polish</strong> &nbsp;·&nbsp;
+  <strong>Spanish</strong>
+</p>
+
+> **Preview status:** Language coverage is intentionally limited in this
+> release. For the best results, use one of the 11 recommended languages
+> above. Broader multilingual coverage and Chinese dialect support are
+> planned for future releases.
+
+## Model Details
+
+Audio8 TTS uses a DualAR architecture inspired by
+[Fish Audio S2 Pro](https://github.com/fishaudio/fish-speech). The slow AR
+transformer predicts one semantic token for each audio frame. The fast AR
+transformer predicts the frame's codec codebooks, conditioned on the slow
+hidden state and preceding codebooks.
+
+| Component | Configuration |
+|---|---|
+| Main model | 601,159,424 parameters, excluding the codec |
+| Slow AR | 24 layers, width 896, 14 attention heads, 2 KV heads |
+| Fast AR | 4 layers, width 896, 14 attention heads, 2 KV heads |
+| Acoustic tokens | 10 codebooks, 4,096 entries per codebook |
+| Codec | 44.1 kHz, 2,048 samples per model frame (~21.5 frames/s) |
+| Context | Up to 2,048 packed text/audio positions |
+| Execution provider | ONNX Runtime CPU |
+
+## Quick Start
+
+Python 3.11 or newer is required. The current release is tested on macOS
+arm64.
+
+### 1. Download the code and model
+
+```bash
+git clone https://github.com/Audio8-AI/Audio8_TTS.git
+cd Audio8_TTS/onnx_runtime
+
+python3 -m pip install -U "huggingface_hub[cli]"
+hf download Audio8/Audio8-TTS-Preview-0.6B-ONNX-INT4 --local-dir model
+bash setup.sh
+```
+
+The model files are stored at this Hugging Face repository's root. Downloading
+with `--local-dir model` creates the exact layout expected by the runtime:
+
+```text
+model/
+├── slow_ar_int4.onnx(.data)
+├── fast_ar_int4.onnx(.data)
+├── codec_decoder_fp16.onnx(.data)
+├── runtime_manifest.json
+├── tokenizer/tokenizer.json
+└── registration/
+    ├── codec_encoder_fp16.onnx(.data)
+    └── registration_manifest.json
+```
+
+### 2. Register a reference voice
+
+Start the local service and open <http://127.0.0.1:8024>. Upload a 0.5-30
+second reference recording, its exact transcript, and a voice name.
+
+```bash
+bash start_server.sh
+```
+
+The same operation is available through HTTP:
+
+```bash
+curl http://127.0.0.1:8024/api/voices/register \
+  -F 'audio=@/absolute/path/reference.wav' \
+  -F 'text=The exact transcript of the reference recording.' \
+  -F 'name=speaker_a' \
+  -F 'overwrite=false'
+```
+
+The encoder in `registration/` is loaded only while registering a voice. The
+generated profile is stored locally and can be reused across requests.
+
+### 3. Generate speech
+
+```bash
+bash run_infer.sh \
+  --text "Welcome to Audio8 TTS ONNX Runtime." \
+  --voice speaker_a \
+  --max-new-tokens 256 \
+  --output outputs/example.wav
+```
+
+The command writes `outputs/example.wav` and `[10, T]` codec codes to
+`outputs/example.npy`.
+
+### HTTP API
+
+```bash
+curl http://127.0.0.1:8024/api/tts \
+  -H 'Content-Type: application/json' \
+  -d '{"text":"Welcome to Audio8 TTS.","voice_name":"speaker_a","max_new_tokens":256}' \
+  -o outputs/api.wav
+```
+
+### OpenAI-compatible API
+
+```bash
+curl http://127.0.0.1:8024/v1/audio/speech \
+  -H 'Content-Type: application/json' \
+  -d '{"model":"arktts","input":"Welcome to Audio8 TTS.","voice":"speaker_a","response_format":"wav"}' \
+  -o outputs/openai.wav
+```
+
+See the complete
+[ONNX Runtime guide](https://github.com/Audio8-AI/Audio8_TTS/tree/master/onnx_runtime)
+for streaming output, configuration, memory management, and service controls.
+
+## Evaluation
+
+The source Audio8 TTS Preview checkpoint is a compact first-tier model on
+Seed-TTS and CV3 multilingual evaluation. See the
+[base model card](https://huggingface.co/Audio8/Audio8-TTS-Preview-0.6b#evaluation)
+for benchmark tables, methodology, and comparison notes.
+
+INT4 quantization can change sampled token sequences, so quality should be
+evaluated for each target language, voice, and deployment setting rather than
+assuming bit-for-bit equivalence with the source checkpoint.
+
+## Limitations and Responsible Use
+
+- This is a Preview checkpoint with limited multilingual and dialect coverage.
+- Very long, noisy, or incorrectly transcribed references can reduce stability
+  and speaker similarity.
+- Generated speech can be misused for impersonation or misinformation. Obtain
+  consent before cloning a voice and clearly disclose synthetic audio where
+  appropriate.
+- Evaluate the model for accuracy, safety, and legal compliance before
+  deployment.
+
+## License and Acknowledgements
+
+The code and model weights are released under the
+[Apache License 2.0](https://github.com/Audio8-AI/Audio8_TTS/blob/master/LICENSE).
+See the upstream
+[NOTICE](https://github.com/Audio8-AI/Audio8_TTS/blob/master/NOTICE) for
+attribution details.
+
+We thank the Fish Audio team for publishing the DualAR architecture used in
+Fish Audio S2 Pro.

codec_decoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e379be31db6c1b0c111e0e3d2aeb10717ee96b197462b926de411e75a1fd019
+size 594319

codec_decoder_fp16.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18838f686aa7c1528fb69ec11e1ab404fdc4dc823d13219abfd4b327988527c0
+size 260741440

fast_ar_int4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808c5a0c95c28d90337d925a9a8f6075f7ff8eb7b3080d2b34c4133479a6dc94
+size 156318

fast_ar_int4.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183be0c9f26b27c605b92a0875beb93f8f98b771f27f65cab133c73610868325
+size 35055104

licenses/Apache-2.0.txt

@@ -0,0 +1,171 @@
+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.
+
+"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. 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. "Submitted"
+means any form of electronic, verbal, or written communication sent to the
+Licensor or its representatives, excluding communication 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 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;
+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 copyright statement to Your modifications and may
+provide additional or different license terms and conditions for use,
+reproduction, or distribution of Your modifications, provided that 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.
+
+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 arising as a
+result of this License or out of the use or inability to use the Work, 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.

licenses/Audio8-NOTICE.txt

@@ -0,0 +1,4 @@
+audio8_tts
+
+The model architecture is inspired by the DualAR design used in Fish Audio
+S2 Pro.

runtime_manifest.json

@@ -0,0 +1,42 @@
+{
+  "model_family": "audio8_tts",
+  "activation_dtype": "float16",
+  "slow_logits_layout": "semantic_then_eos",
+  "slow_logits_size": 4097,
+  "kv_attention_layout": "valid_prefix",
+  "max_seq_len": 2048,
+  "num_layers": 24,
+  "num_fast_layers": 4,
+  "num_codebooks": 10,
+  "n_local_heads": 2,
+  "fast_n_local_heads": 2,
+  "head_dim": 64,
+  "fast_head_dim": 64,
+  "fast_dim": 896,
+  "vocab_size": 155776,
+  "codebook_size": 4096,
+  "semantic_begin_id": 151678,
+  "semantic_end_id": 155773,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "codec_sample_rate": 44100,
+  "codec_frame_size": 2048,
+  "sample_rate": 44100,
+  "codec_hop_length": 2048,
+  "stream_context_frames": 128,
+  "stream_guard_frames": 1,
+  "decoder_provider": "cpu",
+  "default_codec_precision": "fp16",
+  "available_codec_precisions": [
+    "fp16"
+  ],
+  "codec_models": {
+    "fp16": "codec_decoder_fp16.onnx"
+  },
+  "im_end_id": 151645,
+  "model_fingerprint": "62dcff0adf6c2535b3260467a7c1d482b556da57266c96a444518b76e140d2c3",
+  "default_precision": "int4",
+  "available_precisions": [
+    "int4"
+  ]
+}

slow_ar_int4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf7701d6da81f888b49ba6e752445d9786a9915ba30dcf084f7743bdda96834
+size 900218

slow_ar_int4.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb217f654039692204386b7e5b74d98e9268863bb664a849aa123a9053d6c824
+size 290267090

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24e08099d45a8adf3f52f5f0b03276e433bb9d689bb15fcbcc48ce58744588b
+size 12217872