Add files using upload-large-folder tool

.gitattributes

@@ -38,3 +38,14 @@ clip/ltx23/ltx-2.3_text_projection_bf16.safetensors filter=lfs diff=lfs merge=lf
 checkpoints/xl/rs_pleasurechest_v2.safetensors filter=lfs diff=lfs merge=lfs -text
 unet/flux/v_reaflux_v10FP8.safetensors filter=lfs diff=lfs merge=lfs -text
 diffusion_models/ltx2/ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoints/xl/rta_copaxTimeless_xplus2BNSFW1.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoints/xl/rt_artemisLuxe_matureFLAT20.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoints/xl/rt_perfectdeliberate_v90.safetensors filter=lfs diff=lfs merge=lfs -text
+omnivoice/OmniVoice/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Wan2.2/wb_dasiwaWAN22I2V14BLightspeed_boundbite_high_V10.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/zi/zp_moodyPornMix_zitV11DPO.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Wan2.2/wb_dasiwaWAN22I2V14BLightspeed_boundbite_low_V10.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Wan2.2/smoothMix2214BI2V_i2v_low.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Wan2.2/smoothMix2214BI2V_i2v_high.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/zi/zpw_nsfwProjectAnime_v10FP16.safetensors filter=lfs diff=lfs merge=lfs -text
+diffusion_models/cocomix/copaxTimeless_qwenUnreal_Overcooked_bf16.safetensors filter=lfs diff=lfs merge=lfs -text

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/.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

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/README.md

@@ -0,0 +1,1315 @@
+---
+license: apache-2.0
+---
+
+# Qwen3-TTS
+
+## Overview
+### Introduction
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/qwen3_tts_introduction.png" width="90%"/>
+<p>
+
+Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs. In addition, the models feature strong contextual understanding, enabling adaptive control of tone, speaking rate, and emotional expression based on instructions and text semantics, and they show markedly improved robustness to noisy input text. Key features:
+
+* **Powerful Speech Representation**: Powered by the self-developed Qwen3-TTS-Tokenizer-12Hz, it achieves efficient acoustic compression and high-dimensional semantic modeling of speech signals. It fully preserves paralinguistic information and acoustic environmental features, enabling high-speed, high-fidelity speech reconstruction through a lightweight non-DiT architecture.
+* **Universal End-to-End Architecture**: Utilizing a discrete multi-codebook LM architecture, it realizes full-information end-to-end speech modeling. This completely bypasses the information bottlenecks and cascading errors inherent in traditional LM+DiT schemes, significantly enhancing the model’s versatility, generation efficiency, and performance ceiling.
+* **Extreme Low-Latency Streaming Generation**: Based on the innovative Dual-Track hybrid streaming generation architecture, a single model supports both streaming and non-streaming generation. It can output the first audio packet immediately after a single character is input, with end-to-end synthesis latency as low as 97ms, meeting the rigorous demands of real-time interactive scenarios.
+* **Intelligent Text Understanding and Voice Control**: Supports speech generation driven by natural language instructions, allowing for flexible control over multi-dimensional acoustic attributes such as timbre, emotion, and prosody. By deeply integrating text semantic understanding, the model adaptively adjusts tone, rhythm, and emotional expression, achieving lifelike “what you imagine is what you hear” output.
+
+
+### Model Architecture
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/overview.png" width="80%"/>
+<p>
+
+### Released Models Description and Download
+
+Below is an introduction and download information for the Qwen3-TTS models that have already been released. Other models mentioned in the technical report will be released in the near future. Please select and download the model that fits your needs.
+
+| Tokenizer Name                      | Description |
+|---------------------------------|-------------|
+| Qwen3-TTS-Tokenizer-12Hz        | The Qwen3-TTS-Tokenizer-12Hz model which can encode the input speech into codes and decode them back into speech. |
+
+
+| Model | Features | Language Support | Streaming | Instruction Control |
+|---|---|---|---|---|
+| Qwen3-TTS-12Hz-1.7B-VoiceDesign | Performs voice design based on user-provided descriptions. | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian | ✅ | ✅ |
+| Qwen3-TTS-12Hz-1.7B-CustomVoice | Provides style control over target timbres via user instructions; supports 9 premium timbres covering various combinations of gender, age, language, and dialect. | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian | ✅ | ✅ |
+| Qwen3-TTS-12Hz-1.7B-Base | Base model capable of 3-second rapid voice clone from user audio input; can be used for fine-tuning (FT) other models. | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian | ✅ |  |
+| Qwen3-TTS-12Hz-0.6B-CustomVoice | Supports 9 premium timbres covering various combinations of gender, age, language, and dialect. | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian | ✅ |  |
+| Qwen3-TTS-12Hz-0.6B-Base | Base model capable of 3-second rapid voice clone from user audio input; can be used for fine-tuning (FT) other models. | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian | ✅ |  |
+
+During model loading in the qwen-tts package or vLLM, model weights will be automatically downloaded based on the model name. However, if your runtime environment is not conducive to downloading weights during execution, you can refer to the following commands to manually download the model weights to a local directory:
+
+```bash
+# Download through ModelScope (recommended for users in Mainland China)
+pip install -U modelscope
+modelscope download --model Qwen/Qwen3-TTS-Tokenizer-12Hz  --local_dir ./Qwen3-TTS-Tokenizer-12Hz 
+modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
+modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local_dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
+modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-Base --local_dir ./Qwen3-TTS-12Hz-1.7B-Base
+modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local_dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
+modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-Base --local_dir ./Qwen3-TTS-12Hz-0.6B-Base
+
+# Download through Hugging Face
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz --local-dir ./Qwen3-TTS-Tokenizer-12Hz
+huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice
+huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --local-dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign
+huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base --local-dir ./Qwen3-TTS-12Hz-1.7B-Base
+huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local-dir ./Qwen3-TTS-12Hz-0.6B-CustomVoice
+huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base --local-dir ./Qwen3-TTS-12Hz-0.6B-Base
+```
+
+
+## Quickstart
+
+### Environment Setup
+
+The easiest way to quickly use Qwen3-TTS is to install the `qwen-tts` Python package from PyPI. This will pull in the required runtime dependencies and allow you to load any released Qwen3-TTS model. We recommend using a **fresh, isolated environment** to avoid dependency conflicts with existing packages. You can create a clean Python 3.12 environment like this:
+
+```bash
+conda create -n qwen3-tts python=3.12 -y
+conda activate qwen3-tts
+```
+
+then run:
+
+```bash
+pip install -U qwen-tts
+```
+
+If you want to develop or modify the code locally, install from source in editable mode.
+
+```bash
+git clone https://github.com/QwenLM/Qwen3-TTS.git
+cd Qwen3-TTS
+pip install -e .
+```
+
+Additionally, we recommend using FlashAttention 2 to reduce GPU memory usage.
+
+```bash
+pip install -U flash-attn --no-build-isolation
+```
+
+If your machine has less than 96GB of RAM and lots of CPU cores, run:
+
+```bash
+MAX_JOBS=4 pip install -U flash-attn --no-build-isolation
+```
+
+Also, you should have hardware that is compatible with FlashAttention 2. Read more about it in the official documentation of the [FlashAttention repository](https://github.com/Dao-AILab/flash-attention). FlashAttention 2 can only be used when a model is loaded in `torch.float16` or `torch.bfloat16`.
+
+
+### Python Package Usage
+
+After installation, you can import `Qwen3TTSModel` to run custom voice TTS, voice design, and voice clone. The model weights can be specified either as a Hugging Face model id (recommended) or as a local directory path you downloaded. For all the `generate_*` functions below, besides the parameters shown and explicitly documented, you can also pass generation kwargs supported by Hugging Face Transformers `model.generate`, e.g., `max_new_tokens`, `top_p`, etc.
+
+#### Custom Voice Generate
+
+For custom voice models (`Qwen3-TTS-12Hz-1.7B/0.6B-CustomVoice`), you just need to call `generate_custom_voice`, passing a single string or a batch list, along with `language`, `speaker`, and optional `instruct`. You can also call `model.get_supported_speakers()` and `model.get_supported_languages()` to see which speakers and languages the current model supports.
+
+```python
+import torch
+import soundfile as sf
+from qwen_tts import Qwen3TTSModel
+
+model = Qwen3TTSModel.from_pretrained(
+    "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+
+# single inference
+wavs, sr = model.generate_custom_voice(
+    text="其实我真的有发现，我是一个特别善于观察别人情绪的人。",
+    language="Chinese", # Pass `Auto` (or omit) for auto language adaptive; if the target language is known, set it explicitly.
+    speaker="Vivian",
+    instruct="用特别愤怒的语气说", # Omit if not needed.
+)
+sf.write("output_custom_voice.wav", wavs[0], sr)
+
+# batch inference
+wavs, sr = model.generate_custom_voice(
+    text=[
+        "其实我真的有发现，我是一个特别善于观察别人情绪的人。", 
+        "She said she would be here by noon."
+    ],
+    language=["Chinese", "English"],
+    speaker=["Vivian", "Ryan"],
+    instruct=["", "Very happy."]
+)
+sf.write("output_custom_voice_1.wav", wavs[0], sr)
+sf.write("output_custom_voice_2.wav", wavs[1], sr)
+```
+
+For `Qwen3-TTS-12Hz-1.7B/0.6B-CustomVoice` models, the supported speaker list and speaker descriptions are provided below. We recommend using each speaker’s native language for the best quality. Of course, each speaker can speak any language supported by the model.
+
+| Speaker | Voice Description  |  Native language |
+| --- | --- | --- |
+| Vivian | Bright, slightly edgy young female voice. | Chinese |
+| Serena | Warm, gentle young female voice. | Chinese |
+| Uncle_Fu | Seasoned male voice with a low, mellow timbre. | Chinese |
+| Dylan | Youthful Beijing male voice with a clear, natural timbre. | Chinese (Beijing Dialect) |
+| Eric | Lively Chengdu male voice with a slightly husky brightness. | Chinese (Sichuan Dialect) |
+| Ryan | Dynamic male voice with strong rhythmic drive. | English |
+| Aiden | Sunny American male voice with a clear midrange. | English |
+| Ono_Anna | Playful Japanese female voice with a light, nimble timbre. | Japanese |
+| Sohee | Warm Korean female voice with rich emotion. | Korean |
+
+#### Voice Design
+
+For the voice design model (`Qwen3-TTS-12Hz-1.7B-VoiceDesign`), you can use `generate_voice_design` to provide the target text and a natural-language `instruct` description.
+
+```python
+import torch
+import soundfile as sf
+from qwen_tts import Qwen3TTSModel
+
+model = Qwen3TTSModel.from_pretrained(
+    "Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+
+# single inference
+wavs, sr = model.generate_voice_design(
+    text="哥哥，你回来啦，人家等了你好久好久了，要抱抱！",
+    language="Chinese",
+    instruct="体现撒娇稚嫩的萝莉女声，音调偏高且起伏明显，营造出黏人、做作又刻意卖萌的听觉效果。",
+)
+sf.write("output_voice_design.wav", wavs[0], sr)
+
+# batch inference
+wavs, sr = model.generate_voice_design(
+    text=[
+      "哥哥，你回来啦，人家等了你好久好久了，要抱抱！",
+      "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!"
+    ],
+    language=["Chinese", "English"],
+    instruct=[
+      "体现撒娇稚嫩的萝莉女声，音调偏高且起伏明显，营造出黏人、做作又刻意卖萌的听觉效果。",
+      "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice."
+    ]
+)
+sf.write("output_voice_design_1.wav", wavs[0], sr)
+sf.write("output_voice_design_2.wav", wavs[1], sr)
+```
+
+#### Voice Clone
+
+For the voice clone model (`Qwen3-TTS-12Hz-1.7B/0.6B-Base`), to clone a voice and synthesize new content, you just need to provide a reference audio clip (`ref_audio`) along with its transcript (`ref_text`). `ref_audio` can be a local file path, a URL, a base64 string, or a `(numpy_array, sample_rate)` tuple. If you set `x_vector_only_mode=True`, only the speaker embedding is used so `ref_text` is not required, but cloning quality may be reduced.
+
+```python
+import torch
+import soundfile as sf
+from qwen_tts import Qwen3TTSModel
+
+model = Qwen3TTSModel.from_pretrained(
+    "Qwen/Qwen3-TTS-12Hz-1.7B-Base",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+
+ref_audio = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav"
+ref_text  = "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it! And thanks to you."
+
+wavs, sr = model.generate_voice_clone(
+    text="I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it's a disaster (◍•͈⌔•͈◍), very sad!",
+    language="English",
+    ref_audio=ref_audio,
+    ref_text=ref_text,
+)
+sf.write("output_voice_clone.wav", wavs[0], sr)
+```
+
+If you need to reuse the same reference prompt across multiple generations (to avoid recomputing prompt features), build it once with `create_voice_clone_prompt` and pass it via `voice_clone_prompt`.
+
+```python
+prompt_items = model.create_voice_clone_prompt(
+    ref_audio=ref_audio,
+    ref_text=ref_text,
+    x_vector_only_mode=False,
+)
+wavs, sr = model.generate_voice_clone(
+    text=["Sentence A.", "Sentence B."],
+    language=["English", "English"],
+    voice_clone_prompt=prompt_items,
+)
+sf.write("output_voice_clone_1.wav", wavs[0], sr)
+sf.write("output_voice_clone_2.wav", wavs[1], sr)
+```
+
+For more examples of reusable voice clone prompts, batch cloning, and batch inference, please refer to the [example codes](https://github.com/QwenLM/Qwen3-TTS/blob/main/examples/test_model_12hz_base.py). With those examples and the `generate_voice_clone` function description, you can explore more advanced usage patterns.
+
+#### Voice Design then Clone
+
+If you want a designed voice that you can reuse like a cloned speaker, a practical workflow is: (1) use the **VoiceDesign** model to synthesize a short reference clip that matches your target persona, (2) feed that clip into `create_voice_clone_prompt` to build a reusable prompt, and then (3) call `generate_voice_clone` with `voice_clone_prompt` to generate new content without re-extracting features every time. This is especially useful when you want a consistent character voice across many lines.
+
+```python
+import torch
+import soundfile as sf
+from qwen_tts import Qwen3TTSModel
+
+# create a reference audio in the target style using the VoiceDesign model
+design_model = Qwen3TTSModel.from_pretrained(
+    "Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+
+ref_text = "H-hey! You dropped your... uh... calculus notebook? I mean, I think it's yours? Maybe?"
+ref_instruct = "Male, 17 years old, tenor range, gaining confidence - deeper breath support now, though vowels still tighten when nervous"
+ref_wavs, sr = design_model.generate_voice_design(
+    text=ref_text,
+    language="English",
+    instruct=ref_instruct
+)
+sf.write("voice_design_reference.wav", ref_wavs[0], sr)
+
+# build a reusable clone prompt from the voice design reference
+clone_model = Qwen3TTSModel.from_pretrained(
+    "Qwen/Qwen3-TTS-12Hz-1.7B-Base",
+    device_map="cuda:0",
+    dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+)
+
+voice_clone_prompt = clone_model.create_voice_clone_prompt(
+    ref_audio=(ref_wavs[0], sr),   # or "voice_design_reference.wav"
+    ref_text=ref_text,
+)
+
+sentences = [
+    "No problem! I actually... kinda finished those already? If you want to compare answers or something...",
+    "What? No! I mean yes but not like... I just think you're... your titration technique is really precise!",
+]
+
+# reuse it for multiple single calls
+wavs, sr = clone_model.generate_voice_clone(
+    text=sentences[0],
+    language="English",
+    voice_clone_prompt=voice_clone_prompt,
+)
+sf.write("clone_single_1.wav", wavs[0], sr)
+
+wavs, sr = clone_model.generate_voice_clone(
+    text=sentences[1],
+    language="English",
+    voice_clone_prompt=voice_clone_prompt,
+)
+sf.write("clone_single_2.wav", wavs[0], sr)
+
+# or batch generate in one call
+wavs, sr = clone_model.generate_voice_clone(
+    text=sentences,
+    language=["English", "English"],
+    voice_clone_prompt=voice_clone_prompt,
+)
+for i, w in enumerate(wavs):
+    sf.write(f"clone_batch_{i}.wav", w, sr)
+```
+
+#### Tokenizer Encode and Decode
+
+If you only want to encode and decode audio for transport or training and so on, `Qwen3TTSTokenizer` supports encode/decode with paths, URLs, numpy waveforms, and dict/list payloads, for example:
+
+```python
+import soundfile as sf
+from qwen_tts import Qwen3TTSTokenizer
+
+tokenizer = Qwen3TTSTokenizer.from_pretrained(
+    "Qwen/Qwen3-TTS-Tokenizer-12Hz",
+    device_map="cuda:0",
+)
+
+enc = tokenizer.encode("https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/tokenizer_demo_1.wav")
+wavs, sr = tokenizer.decode(enc)
+sf.write("decode_output.wav", wavs[0], sr)
+```
+
+For more tokenizer examples (including different input formats and batch usage), please refer to the [example codes](https://github.com/QwenLM/Qwen3-TTS/blob/main/examples/test_tokenizer_12hz.py). With those examples and the description for `Qwen3TTSTokenizer`, you can explore more advanced usage patterns.
+
+### Launch Local Web UI Demo
+
+To launch the Qwen3-TTS web ui demo, simply install the `qwen-tts` package and run `qwen-tts-demo`. Use the command below for help:
+
+```bash
+qwen-tts-demo --help
+```
+
+To launch the demo, you can use the following commands:
+
+```bash
+# CustomVoice model
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --ip 0.0.0.0 --port 8000
+# VoiceDesign model
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign --ip 0.0.0.0 --port 8000
+# Base model
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --ip 0.0.0.0 --port 8000
+```
+
+And then open `http://<your-ip>:8000`, or access it via port forwarding in tools like VS Code.
+
+#### Base Model HTTPS Notes
+
+To avoid browser microphone permission issues after deploying the server, for Base model deployments, it is recommended/required to run the gradio service over **HTTPS** (especially when accessed remotely or behind modern browsers/gateways). Use `--ssl-certfile` and `--ssl-keyfile` to enable HTTPS. First we need to generate a private key and a self-signed cert (valid for 365 days):
+
+```bash
+openssl req -x509 -newkey rsa:2048 \
+  -keyout key.pem -out cert.pem \
+  -days 365 -nodes \
+  -subj "/CN=localhost"
+```
+
+Then run the demo with HTTPS:
+
+```bash
+qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base \
+  --ip 0.0.0.0 --port 8000 \
+  --ssl-certfile cert.pem \
+  --ssl-keyfile key.pem \
+  --no-ssl-verify
+```
+
+And open `https://<your-ip>:8000` to experience it. If your browser shows a warning, it’s expected for self-signed certificates. For production, use a real certificate.
+
+### DashScope API Usage
+
+To further explore Qwen3-TTS, we encourage you to try our DashScope API for a faster and more efficient experience. For detailed API information and documentation, please refer to the following:
+
+| API Description | API Documentation (Mainland China) | API Documentation (International) |
+|------------------|-----------------------------------|------------------------------------|
+| Real-time API for Qwen3-TTS of custom voice model. | [https://help.aliyun.com/zh/model-studio/qwen-tts-realtime](https://help.aliyun.com/zh/model-studio/qwen-tts-realtime) | [https://www.alibabacloud.com/help/en/model-studio/qwen-tts-realtime](https://www.alibabacloud.com/help/en/model-studio/qwen-tts-realtime) |
+| Real-time API for Qwen3-TTS of voice clone model. | [https://help.aliyun.com/zh/model-studio/qwen-tts-voice-cloning](https://help.aliyun.com/zh/model-studio/qwen-tts-voice-cloning) | [https://www.alibabacloud.com/help/en/model-studio/qwen-tts-voice-cloning](https://www.alibabacloud.com/help/en/model-studio/qwen-tts-voice-cloning) |
+| Real-time API for Qwen3-TTS of voice design model. | [https://help.aliyun.com/zh/model-studio/qwen-tts-voice-design](https://help.aliyun.com/zh/model-studio/qwen-tts-voice-design) | [https://www.alibabacloud.com/help/en/model-studio/qwen-tts-voice-design](https://www.alibabacloud.com/help/en/model-studio/qwen-tts-voice-design) |
+
+
+## vLLM Usage
+
+vLLM officially provides day-0 support for Qwen3-TTS! Welcome to use vLLM-Omni for Qwen3-TTS deployment and inference. For installation and more details, please check [vLLM-Omni official documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/quickstart/#installation). Now only offline inference is supported. Online serving will be supported later, and vLLM-Omni will continue to offer support and optimization for Qwen3-TTS in areas such as inference speed and streaming capabilities.
+
+### Offline Inference
+You can use vLLM-Omni to inference Qwen3-TTS locally, we provide examples in [vLLM-Omni repo](https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/qwen3_tts) which can generate audio output:
+```bash
+# git clone https://github.com/vllm-project/vllm-omni.git
+
+# cd vllm-omni/examples/offline_inference/qwen3_tts
+
+# Run a single sample with CustomVoice task
+python end2end.py --query-type CustomVoice
+
+# Batch sample (multiple prompts in one run) with CustomVoice task:
+python end2end.py --query-type CustomVoice --use-batch-sample
+
+# Run a single sample with VoiceDesign task
+python end2end.py --query-type VoiceDesign
+
+# Batch sample (multiple prompts in one run) with VoiceDesign task:
+python end2end.py --query-type VoiceDesign --use-batch-sample
+
+# Run a single sample with Base task in icl mode-tag
+python end2end.py --query-type Base --mode-tag icl
+```
+
+## Evaluation
+
+During evaluation, we ran inference for all models with `dtype=torch.bfloat16` and set `max_new_tokens=2048`. All other sampling parameters used the defaults from the checkpoint’s `generate_config.json`. For the Seed-Test and InstructTTS-Eval test sets, we set `language="auto"`, while for all other test sets we explicitly passed the corresponding `language`. The detailed results are shown below.
+
+
+<details>
+<summary>Speech Generation Benchmarks</summary>
+
+*Zero-shot speech generation on the Seed-TTS test set. Performance is measured by Word Error Rate (WER, ↓), where lower is better.*
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: center;">Datasets</th>
+      <th style="text-align: left;">Model</th>
+      <th colspan="2" style="text-align: center;">Performance</th>
+    </tr>
+    <tr style="border-bottom: 1px solid #ddd; border-top: 1px solid #ddd;">
+      <td colspan="4" style="text-align: center;"><em>Content Consistency</em></td>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="14" style="text-align: center; vertical-align: middle;">SEED<br><em>test-zh</em> | <em>test-en</em></td>
+      <td style="text-align: left;">Seed-TTS (Anastassiou et al., 2024)</td>
+      <td style="text-align: center;">1.12</td>
+      <td style="text-align: center;">2.25</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MaskGCT (Wang et al., 2024)</td>
+      <td style="text-align: center;">2.27</td>
+      <td style="text-align: center;">2.62</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">E2 TTS (Eskimez et al., 2024)</td>
+      <td style="text-align: center;">1.97</td>
+      <td style="text-align: center;">2.19</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">F5-TTS (Chen et al., 2024)</td>
+      <td style="text-align: center;">1.56</td>
+      <td style="text-align: center;">1.83</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spark TTS (Wang et al., 2025)</td>
+      <td style="text-align: center;">1.20</td>
+      <td style="text-align: center;">1.98</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Llasa-8B (Ye et al., 2025b)</td>
+      <td style="text-align: center;">1.59</td>
+      <td style="text-align: center;">2.97</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">KALL-E (Xia et al., 2024)</td>
+      <td style="text-align: center;">0.96</td>
+      <td style="text-align: center;">1.94</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">FireRedTTS 2 (Xie et al., 2025)</td>
+      <td style="text-align: center;">1.14</td>
+      <td style="text-align: center;">1.95</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">CosyVoice 3 (Du et al., 2025)</td>
+      <td style="text-align: center;"><strong>0.71</strong></td>
+      <td style="text-align: center;">1.45</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MiniMax-Speech (Zhang et al., 2025a)</td>
+      <td style="text-align: center;">0.83</td>
+      <td style="text-align: center;">1.65</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-25Hz-0.6B-Base</td>
+      <td style="text-align: center;">1.18</td>
+      <td style="text-align: center;">1.64</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-25Hz-1.7B-Base</td>
+      <td style="text-align: center;">1.10</td>
+      <td style="text-align: center;">1.49</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-12Hz-0.6B-Base</td>
+      <td style="text-align: center;">0.92</td>
+      <td style="text-align: center;">1.32</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-12Hz-1.7B-Base</td>
+      <td style="text-align: center;">0.77</td>
+      <td style="text-align: center;"><strong>1.24</strong></td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Multilingual speech generation on the TTS multilingual test set. Performance is measured by Word Error Rate (WER, ↓) for content consistency and Cosine Similarity (SIM, ↑) for speaker similarity.*
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2" style="text-align: left; vertical-align: bottom;">Language</th>
+      <th colspan="2" style="text-align: center;">Qwen3-TTS-25Hz</th>
+      <th colspan="2" style="text-align: center;">Qwen3-TTS-12Hz</th>
+      <th rowspan="2" style="text-align: center; vertical-align: bottom;">MiniMax</th>
+      <th rowspan="2" style="text-align: center; vertical-align: bottom;">ElevenLabs</th>
+    </tr>
+    <tr>
+      <th style="text-align: center;">0.6B-Base</th>
+      <th style="text-align: center;">1.7B-Base</th>
+      <th style="text-align: center;">0.6B-Base</th>
+      <th style="text-align: center;">1.7B-Base</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="7" style="text-align: center; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;"><em>Content Consistency</em></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Chinese</td>
+      <td style="text-align: center;">1.108</td>
+      <td style="text-align: center;"><strong>0.777</strong></td>
+      <td style="text-align: center;">1.145</td>
+      <td style="text-align: center;">0.928</td>
+      <td style="text-align: center;">2.252</td>
+      <td style="text-align: center;">16.026</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">English</td>
+      <td style="text-align: center;">1.048</td>
+      <td style="text-align: center;">1.014</td>
+      <td style="text-align: center;"><strong>0.836</strong></td>
+      <td style="text-align: center;">0.934</td>
+      <td style="text-align: center;">2.164</td>
+      <td style="text-align: center;">2.339</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">German</td>
+      <td style="text-align: center;">1.501</td>
+      <td style="text-align: center;">0.960</td>
+      <td style="text-align: center;">1.089</td>
+      <td style="text-align: center;">1.235</td>
+      <td style="text-align: center;">1.906</td>
+      <td style="text-align: center;"><strong>0.572</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Italian</td>
+      <td style="text-align: center;">1.169</td>
+      <td style="text-align: center;">1.105</td>
+      <td style="text-align: center;">1.534</td>
+      <td style="text-align: center;"><strong>0.948</strong></td>
+      <td style="text-align: center;">1.543</td>
+      <td style="text-align: center;">1.743</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Portuguese</td>
+      <td style="text-align: center;">2.046</td>
+      <td style="text-align: center;">1.778</td>
+      <td style="text-align: center;">2.254</td>
+      <td style="text-align: center;">1.526</td>
+      <td style="text-align: center;">1.877</td>
+      <td style="text-align: center;"><strong>1.331</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spanish</td>
+      <td style="text-align: center;">2.031</td>
+      <td style="text-align: center;">1.491</td>
+      <td style="text-align: center;">1.491</td>
+      <td style="text-align: center;">1.126</td>
+      <td style="text-align: center;"><strong>1.029</strong></td>
+      <td style="text-align: center;">1.084</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Japanese</td>
+      <td style="text-align: center;">4.189</td>
+      <td style="text-align: center;">5.121</td>
+      <td style="text-align: center;">6.404</td>
+      <td style="text-align: center;">3.823</td>
+      <td style="text-align: center;"><strong>3.519</strong></td>
+      <td style="text-align: center;">10.646</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Korean</td>
+      <td style="text-align: center;">2.852</td>
+      <td style="text-align: center;">2.631</td>
+      <td style="text-align: center;"><strong>1.741</strong></td>
+      <td style="text-align: center;">1.755</td>
+      <td style="text-align: center;">1.747</td>
+      <td style="text-align: center;">1.865</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">French</td>
+      <td style="text-align: center;">2.852</td>
+      <td style="text-align: center;"><strong>2.631</strong></td>
+      <td style="text-align: center;">2.931</td>
+      <td style="text-align: center;">2.858</td>
+      <td style="text-align: center;">4.099</td>
+      <td style="text-align: center;">5.216</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Russian</td>
+      <td style="text-align: center;">5.957</td>
+      <td style="text-align: center;">4.535</td>
+      <td style="text-align: center;">4.458</td>
+      <td style="text-align: center;"><strong>3.212</strong></td>
+      <td style="text-align: center;">4.281</td>
+      <td style="text-align: center;">3.878</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td colspan="7" style="text-align: center; border-bottom: 1px solid #ddd;"><em>Speaker Similarity</em></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Chinese</td>
+      <td style="text-align: center;">0.797</td>
+      <td style="text-align: center;">0.796</td>
+      <td style="text-align: center;"><strong>0.811</strong></td>
+      <td style="text-align: center;">0.799</td>
+      <td style="text-align: center;">0.780</td>
+      <td style="text-align: center;">0.677</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">English</td>
+      <td style="text-align: center;">0.811</td>
+      <td style="text-align: center;">0.815</td>
+      <td style="text-align: center;"><strong>0.829</strong></td>
+      <td style="text-align: center;">0.775</td>
+      <td style="text-align: center;">0.756</td>
+      <td style="text-align: center;">0.613</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">German</td>
+      <td style="text-align: center;">0.749</td>
+      <td style="text-align: center;">0.737</td>
+      <td style="text-align: center;">0.769</td>
+      <td style="text-align: center;"><strong>0.775</strong></td>
+      <td style="text-align: center;">0.733</td>
+      <td style="text-align: center;">0.614</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Italian</td>
+      <td style="text-align: center;">0.722</td>
+      <td style="text-align: center;">0.718</td>
+      <td style="text-align: center;">0.792</td>
+      <td style="text-align: center;"><strong>0.817</strong></td>
+      <td style="text-align: center;">0.699</td>
+      <td style="text-align: center;">0.579</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Portuguese</td>
+      <td style="text-align: center;">0.790</td>
+      <td style="text-align: center;">0.783</td>
+      <td style="text-align: center;">0.794</td>
+      <td style="text-align: center;"><strong>0.817</strong></td>
+      <td style="text-align: center;">0.805</td>
+      <td style="text-align: center;">0.711</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spanish</td>
+      <td style="text-align: center;">0.732</td>
+      <td style="text-align: center;">0.731</td>
+      <td style="text-align: center;">0.812</td>
+      <td style="text-align: center;"><strong>0.814</strong></td>
+      <td style="text-align: center;">0.762</td>
+      <td style="text-align: center;">0.615</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Japanese</td>
+      <td style="text-align: center;"><strong>0.810</strong></td>
+      <td style="text-align: center;">0.807</td>
+      <td style="text-align: center;">0.798</td>
+      <td style="text-align: center;">0.788</td>
+      <td style="text-align: center;">0.776</td>
+      <td style="text-align: center;">0.738</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Korean</td>
+      <td style="text-align: center;"><strong>0.824</strong></td>
+      <td style="text-align: center;">0.814</td>
+      <td style="text-align: center;">0.812</td>
+      <td style="text-align: center;">0.799</td>
+      <td style="text-align: center;">0.779</td>
+      <td style="text-align: center;">0.700</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">French</td>
+      <td style="text-align: center;">0.698</td>
+      <td style="text-align: center;">0.703</td>
+      <td style="text-align: center;">0.700</td>
+      <td style="text-align: center;"><strong>0.714</strong></td>
+      <td style="text-align: center;">0.628</td>
+      <td style="text-align: center;">0.535</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Russian</td>
+      <td style="text-align: center;">0.734</td>
+      <td style="text-align: center;">0.744</td>
+      <td style="text-align: center;">0.781</td>
+      <td style="text-align: center;"><strong>0.792</strong></td>
+      <td style="text-align: center;">0.761</td>
+      <td style="text-align: center;">0.676</td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Cross-lingual speech generation on the Cross-Lingual benchmark. Performance is measured by Mixed Error Rate (WER for English, CER for others, ↓).*
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;">Task</th>
+      <th style="text-align: center;">Qwen3-TTS-25Hz-1.7B-Base</th>
+      <th style="text-align: center;">Qwen3-TTS-12Hz-1.7B-Base</th>
+      <th style="text-align: center;">CosyVoice3</th>
+      <th style="text-align: center;">CosyVoice2</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: left;">en-to-zh</td>
+      <td style="text-align: center;">5.66</td>
+      <td style="text-align: center;"><strong>4.77</strong></td>
+      <td style="text-align: center;">5.09</td>
+      <td style="text-align: center;">13.5</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ja-to-zh</td>
+      <td style="text-align: center;">3.92</td>
+      <td style="text-align: center;">3.43</td>
+      <td style="text-align: center;"><strong>3.05</strong></td>
+      <td style="text-align: center;">48.1</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ko-to-zh</td>
+      <td style="text-align: center;">1.14</td>
+      <td style="text-align: center;">1.08</td>
+      <td style="text-align: center;"><strong>1.06</strong></td>
+      <td style="text-align: center;">7.70</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td style="text-align: left;">zh-to-en</td>
+      <td style="text-align: center;">2.91</td>
+      <td style="text-align: center;"><strong>2.77</strong></td>
+      <td style="text-align: center;">2.98</td>
+      <td style="text-align: center;">6.47</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ja-to-en</td>
+      <td style="text-align: center;">3.95</td>
+      <td style="text-align: center;"><strong>3.04</strong></td>
+      <td style="text-align: center;">4.20</td>
+      <td style="text-align: center;">17.1</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ko-to-en</td>
+      <td style="text-align: center;">3.48</td>
+      <td style="text-align: center;"><strong>3.09</strong></td>
+      <td style="text-align: center;">4.19</td>
+      <td style="text-align: center;">11.2</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td style="text-align: left;">zh-to-ja</td>
+      <td style="text-align: center;">9.29</td>
+      <td style="text-align: center;">8.40</td>
+      <td style="text-align: center;"><strong>7.08</strong></td>
+      <td style="text-align: center;">13.1</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">en-to-ja</td>
+      <td style="text-align: center;">7.74</td>
+      <td style="text-align: center;">7.21</td>
+      <td style="text-align: center;"><strong>6.80</strong></td>
+      <td style="text-align: center;">14.9</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ko-to-ja</td>
+      <td style="text-align: center;">4.17</td>
+      <td style="text-align: center;"><strong>3.67</strong></td>
+      <td style="text-align: center;">3.93</td>
+      <td style="text-align: center;">5.86</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td style="text-align: left;">zh-to-ko</td>
+      <td style="text-align: center;">8.12</td>
+      <td style="text-align: center;"><strong>4.82</strong></td>
+      <td style="text-align: center;">14.4</td>
+      <td style="text-align: center;">24.8</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">en-to-ko</td>
+      <td style="text-align: center;">6.83</td>
+      <td style="text-align: center;"><strong>5.14</strong></td>
+      <td style="text-align: center;">5.87</td>
+      <td style="text-align: center;">21.9</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ja-to-ko</td>
+      <td style="text-align: center;">6.86</td>
+      <td style="text-align: center;"><strong>5.59</strong></td>
+      <td style="text-align: center;">7.92</td>
+      <td style="text-align: center;">21.5</td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Controllable speech generation on InstructTTSEval. Performance is measured by Attribute Perception and Synthesis accuracy (APS), Description-Speech Consistency (DSD), and Response Precision (RP).*
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2" style="text-align: left; vertical-align: bottom;">Type</th>
+      <th rowspan="2" style="text-align: left; vertical-align: bottom;">Model</th>
+      <th colspan="3" style="text-align: center;">InstructTTSEval-ZH</th>
+      <th colspan="3" style="text-align: center;">InstructTTSEval-EN</th>
+    </tr>
+    <tr>
+      <th style="text-align: center;">APS (↑)</th>
+      <th style="text-align: center;">DSD (↑)</th>
+      <th style="text-align: center;">RP (↑)</th>
+      <th style="text-align: center;">APS (↑)</th>
+      <th style="text-align: center;">DSD (↑)</th>
+      <th style="text-align: center;">RP (↑)</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="5" style="text-align: left; vertical-align: middle;"><em>Target<br>Speaker</em></td>
+      <td style="text-align: left;">Gemini-flash</td>
+      <td style="text-align: center;">88.2</td>
+      <td style="text-align: center;"><strong>90.9</strong></td>
+      <td style="text-align: center;"><strong>77.3</strong></td>
+      <td style="text-align: center;"><strong>92.3</strong></td>
+      <td style="text-align: center;"><strong>93.8</strong></td>
+      <td style="text-align: center;"><strong>80.1</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Gemini-pro</td>
+      <td style="text-align: center;"><strong>89.0</strong></td>
+      <td style="text-align: center;">90.1</td>
+      <td style="text-align: center;">75.5</td>
+      <td style="text-align: center;">87.6</td>
+      <td style="text-align: center;">86.0</td>
+      <td style="text-align: center;">67.2</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3TTS-25Hz-1.7B-CustomVoice</td>
+      <td style="text-align: center;">83.1</td>
+      <td style="text-align: center;">75.0</td>
+      <td style="text-align: center;">63.0</td>
+      <td style="text-align: center;">79.0</td>
+      <td style="text-align: center;">82.8</td>
+      <td style="text-align: center;">69.3</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3TTS-12Hz-1.7B-CustomVoice</td>
+      <td style="text-align: center;">83.0</td>
+      <td style="text-align: center;">77.8</td>
+      <td style="text-align: center;">61.2</td>
+      <td style="text-align: center;">77.3</td>
+      <td style="text-align: center;">77.1</td>
+      <td style="text-align: center;">63.7</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">GPT-4o-mini-tts</td>
+      <td style="text-align: center;">54.9</td>
+      <td style="text-align: center;">52.3</td>
+      <td style="text-align: center;">46.0</td>
+      <td style="text-align: center;">76.4</td>
+      <td style="text-align: center;">74.3</td>
+      <td style="text-align: center;">54.8</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td rowspan="9" style="text-align: left; vertical-align: middle;"><em>Voice<br>Design</em></td>
+      <td style="text-align: left;">Qwen3TTS-12Hz-1.7B-VD</td>
+      <td style="text-align: center;"><strong>85.2</strong></td>
+      <td style="text-align: center;"><strong>81.1</strong></td>
+      <td style="text-align: center;"><strong>65.1</strong></td>
+      <td style="text-align: center;">82.9</td>
+      <td style="text-align: center;"><strong>82.4</strong></td>
+      <td style="text-align: center;"><strong>68.4</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Mimo-Audio-7B-Instruct (Zhang et al., 2025b)</td>
+      <td style="text-align: center;">75.7</td>
+      <td style="text-align: center;">74.3</td>
+      <td style="text-align: center;">61.5</td>
+      <td style="text-align: center;">80.6</td>
+      <td style="text-align: center;">77.6</td>
+      <td style="text-align: center;">59.5</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">VoiceSculptor (Hu et al., 2026)</td>
+      <td style="text-align: center;">75.7</td>
+      <td style="text-align: center;">64.7</td>
+      <td style="text-align: center;">61.5</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Hume</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>83.0</strong></td>
+      <td style="text-align: center;">75.3</td>
+      <td style="text-align: center;">54.3</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">VoxInstruct (Zhou et al., 2024)</td>
+      <td style="text-align: center;">47.5</td>
+      <td style="text-align: center;">52.3</td>
+      <td style="text-align: center;">42.6</td>
+      <td style="text-align: center;">54.9</td>
+      <td style="text-align: center;">57.0</td>
+      <td style="text-align: center;">39.3</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Parler-tts-mini (Lyth & King, 2024)</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">63.4</td>
+      <td style="text-align: center;">48.7</td>
+      <td style="text-align: center;">28.6</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Parler-tts-large (Lyth & King, 2024)</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">60.0</td>
+      <td style="text-align: center;">45.9</td>
+      <td style="text-align: center;">31.2</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">PromptTTS (Guo et al., 2023)</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">64.3</td>
+      <td style="text-align: center;">47.2</td>
+      <td style="text-align: center;">31.4</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">PromptStyle (Liu et al., 2023)</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">57.4</td>
+      <td style="text-align: center;">46.4</td>
+      <td style="text-align: center;">30.9</td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Target-Speaker Multilingual Speech Generation on the TTS multilingual test set. Performance is measured by Word Error Rate (WER, ↓).*
+
+<table>
+  <thead>
+    <tr>
+      <th rowspan="2" style="text-align: left; vertical-align: bottom;">Language</th>
+      <th colspan="2" style="text-align: center;">Qwen3-TTS-25Hz</th>
+      <th colspan="2" style="text-align: center;">Qwen3-TTS-12Hz</th>
+      <th rowspan="2" style="text-align: center; vertical-align: bottom;">GPT-4o-Audio<br>Preview</th>
+    </tr>
+    <tr>
+      <th style="text-align: center;">0.6B-CustomVoice</th>
+      <th style="text-align: center;">1.7B-CustomVoice</th>
+      <th style="text-align: center;">0.6B-CustomVoice</th>
+      <th style="text-align: center;">1.7B-CustomVoice</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: left;">Chinese</td>
+      <td style="text-align: center;">0.874</td>
+      <td style="text-align: center;"><strong>0.708</strong></td>
+      <td style="text-align: center;">0.944</td>
+      <td style="text-align: center;">0.903</td>
+      <td style="text-align: center;">3.519</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">English</td>
+      <td style="text-align: center;">1.332</td>
+      <td style="text-align: center;">0.936</td>
+      <td style="text-align: center;">1.188</td>
+      <td style="text-align: center;"><strong>0.899</strong></td>
+      <td style="text-align: center;">2.197</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">German</td>
+      <td style="text-align: center;">0.990</td>
+      <td style="text-align: center;"><strong>0.634</strong></td>
+      <td style="text-align: center;">2.722</td>
+      <td style="text-align: center;">1.057</td>
+      <td style="text-align: center;">1.161</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Italian</td>
+      <td style="text-align: center;">1.861</td>
+      <td style="text-align: center;">1.271</td>
+      <td style="text-align: center;">2.545</td>
+      <td style="text-align: center;">1.362</td>
+      <td style="text-align: center;"><strong>1.194</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Portuguese</td>
+      <td style="text-align: center;">1.728</td>
+      <td style="text-align: center;">1.854</td>
+      <td style="text-align: center;">3.219</td>
+      <td style="text-align: center;">2.681</td>
+      <td style="text-align: center;"><strong>1.504</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spanish</td>
+      <td style="text-align: center;">1.309</td>
+      <td style="text-align: center;">1.284</td>
+      <td style="text-align: center;"><strong>1.154</strong></td>
+      <td style="text-align: center;">1.330</td>
+      <td style="text-align: center;">4.000</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Japanese</td>
+      <td style="text-align: center;"><strong>3.875</strong></td>
+      <td style="text-align: center;">4.518</td>
+      <td style="text-align: center;">6.877</td>
+      <td style="text-align: center;">4.924</td>
+      <td style="text-align: center;">5.001</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Korean</td>
+      <td style="text-align: center;">2.202</td>
+      <td style="text-align: center;">2.274</td>
+      <td style="text-align: center;">3.053</td>
+      <td style="text-align: center;"><strong>1.741</strong></td>
+      <td style="text-align: center;">2.763</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">French</td>
+      <td style="text-align: center;">3.865</td>
+      <td style="text-align: center;"><strong>3.080</strong></td>
+      <td style="text-align: center;">3.841</td>
+      <td style="text-align: center;">3.781</td>
+      <td style="text-align: center;">3.605</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Russian</td>
+      <td style="text-align: center;">6.529</td>
+      <td style="text-align: center;"><strong>4.444</strong></td>
+      <td style="text-align: center;">5.809</td>
+      <td style="text-align: center;">4.734</td>
+      <td style="text-align: center;">5.250</td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Long speech generation results. Performance is measured by Word Error Rate (WER, ↓).*
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: center;">Datasets</th>
+      <th style="text-align: left;">Model</th>
+      <th colspan="2" style="text-align: center;">Performance</th>
+    </tr>
+    <tr style="border-bottom: 1px solid #ddd; border-top: 1px solid #ddd;">
+      <td colspan="4" style="text-align: center;"><em>Content Consistency</em></td>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="5" style="text-align: center; vertical-align: middle;"><em>long-zh</em> | <em>long-en</em></td>
+      <td style="text-align: left;">Higgs-Audio-v2 (chunk) (Boson AI, 2025)</td>
+      <td style="text-align: center;">5.505</td>
+      <td style="text-align: center;">6.917</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">VibeVoice (Peng et al., 2025)</td>
+      <td style="text-align: center;">22.619</td>
+      <td style="text-align: center;">1.780</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">VoxCPM (Zhou et al., 2025)</td>
+      <td style="text-align: center;">4.835</td>
+      <td style="text-align: center;">7.474</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-25Hz-1.7B-CustomVoice</td>
+      <td style="text-align: center;"><strong>1.517</strong></td>
+      <td style="text-align: center;"><strong>1.225</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen3-TTS-12Hz-1.7B-CustomVoice</td>
+      <td style="text-align: center;">2.356</td>
+      <td style="text-align: center;">2.812</td>
+    </tr>
+  </tbody>
+</table>
+</details>
+
+
+<details>
+<summary>Speech Tokenizer Benchmarks</summary>
+
+*Comparison between different supervised semantic speech tokenizers on ASR Task.*
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;">Model</th>
+      <th style="text-align: center;">Codebook Size</th>
+      <th style="text-align: center;">FPS</th>
+      <th style="text-align: center;">C.V. EN</th>
+      <th style="text-align: center;">C.V. CN</th>
+      <th style="text-align: center;">Fluers EN</th>
+      <th style="text-align: center;">Fluers CN</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: left;">S3 Tokenizer(VQ) (Du et al., 2024a)</td>
+      <td style="text-align: center;">4096</td>
+      <td style="text-align: center;">50</td>
+      <td style="text-align: center;">12.06</td>
+      <td style="text-align: center;">15.38</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">-</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">S3 Tokenizer(VQ) (Du et al., 2024a)</td>
+      <td style="text-align: center;">4096</td>
+      <td style="text-align: center;">25</td>
+      <td style="text-align: center;">11.56</td>
+      <td style="text-align: center;">18.26</td>
+      <td style="text-align: center;">7.65</td>
+      <td style="text-align: center;">5.03</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">S3 Tokenizer(FSQ) (Du et al., 2024a)</td>
+      <td style="text-align: center;">6561</td>
+      <td style="text-align: center;">25</td>
+      <td style="text-align: center;">10.67</td>
+      <td style="text-align: center;"><strong>7.29</strong></td>
+      <td style="text-align: center;">6.58</td>
+      <td style="text-align: center;">4.43</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen-TTS-Tokenizer-25Hz (Stage 1)</td>
+      <td style="text-align: center;">32768</td>
+      <td style="text-align: center;">25</td>
+      <td style="text-align: center;"><strong>7.51</strong></td>
+      <td style="text-align: center;">10.73</td>
+      <td style="text-align: center;"><strong>3.07</strong></td>
+      <td style="text-align: center;"><strong>4.23</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen-TTS-Tokenizer-25Hz (Stage 2)</td>
+      <td style="text-align: center;">32768</td>
+      <td style="text-align: center;">25</td>
+      <td style="text-align: center;">10.40</td>
+      <td style="text-align: center;">14.99</td>
+      <td style="text-align: center;">4.14</td>
+      <td style="text-align: center;">4.67</td>
+    </tr>
+  </tbody>
+</table>
+
+<br>
+
+*Comparison between different semantic-related speech tokenizers.*
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;">Model</th>
+      <th style="text-align: center;">NQ</th>
+      <th style="text-align: center;">Codebook Size</th>
+      <th style="text-align: center;">FPS</th>
+      <th style="text-align: center;">PESQ_WB</th>
+      <th style="text-align: center;">PESQ_NB</th>
+      <th style="text-align: center;">STOI</th>
+      <th style="text-align: center;">UTMOS</th>
+      <th style="text-align: center;">SIM</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: left;">SpeechTokenizer (Zhang et al., 2023a)</td>
+      <td style="text-align: center;">8</td>
+      <td style="text-align: center;">1024</td>
+      <td style="text-align: center;">50</td>
+      <td style="text-align: center;">2.60</td>
+      <td style="text-align: center;">3.05</td>
+      <td style="text-align: center;">0.92</td>
+      <td style="text-align: center;">3.90</td>
+      <td style="text-align: center;">0.85</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">X-codec (Ye et al., 2025a)</td>
+      <td style="text-align: center;">2</td>
+      <td style="text-align: center;">1024</td>
+      <td style="text-align: center;">50</td>
+      <td style="text-align: center;">2.68</td>
+      <td style="text-align: center;">3.27</td>
+      <td style="text-align: center;">0.86</td>
+      <td style="text-align: center;">4.11</td>
+      <td style="text-align: center;">0.84</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">X-codec 2 (Ye et al., 2025b)</td>
+      <td style="text-align: center;">1</td>
+      <td style="text-align: center;">65536</td>
+      <td style="text-align: center;">50</td>
+      <td style="text-align: center;">2.43</td>
+      <td style="text-align: center;">3.04</td>
+      <td style="text-align: center;">0.92</td>
+      <td style="text-align: center;">4.13</td>
+      <td style="text-align: center;">0.82</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">XY-Tokenizer (Gong et al., 2025)</td>
+      <td style="text-align: center;">8</td>
+      <td style="text-align: center;">1024</td>
+      <td style="text-align: center;">12.5</td>
+      <td style="text-align: center;">2.41</td>
+      <td style="text-align: center;">3.00</td>
+      <td style="text-align: center;">0.91</td>
+      <td style="text-align: center;">3.98</td>
+      <td style="text-align: center;">0.83</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Mimi (Défossez et al., 2024)</td>
+      <td style="text-align: center;">16</td>
+      <td style="text-align: center;">2048</td>
+      <td style="text-align: center;">12.5</td>
+      <td style="text-align: center;">2.88</td>
+      <td style="text-align: center;">3.42</td>
+      <td style="text-align: center;">0.94</td>
+      <td style="text-align: center;">3.87</td>
+      <td style="text-align: center;">0.87</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">FireredTTS 2 Tokenizer (Xie et al., 2025)</td>
+      <td style="text-align: center;">16</td>
+      <td style="text-align: center;">2048</td>
+      <td style="text-align: center;">12.5</td>
+      <td style="text-align: center;">2.73</td>
+      <td style="text-align: center;">3.28</td>
+      <td style="text-align: center;">0.94</td>
+      <td style="text-align: center;">3.88</td>
+      <td style="text-align: center;">0.87</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Qwen-TTS-Tokenizer-12Hz</td>
+      <td style="text-align: center;">16</td>
+      <td style="text-align: center;">2048</td>
+      <td style="text-align: center;">12.5</td>
+      <td style="text-align: center;"><strong>3.21</strong></td>
+      <td style="text-align: center;"><strong>3.68</strong></td>
+      <td style="text-align: center;"><strong>0.96</strong></td>
+      <td style="text-align: center;"><strong>4.16</strong></td>
+      <td style="text-align: center;"><strong>0.95</strong></td>
+    </tr>
+  </tbody>
+</table>
+
+</details>
+
+
+## Citation
+
+If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
+
+```BibTeX
+@article{Qwen3-TTS,
+  title={Qwen3-TTS Technical Report},
+  author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
+  journal={arXiv preprint arXiv:2601.15621},
+  year={2026}
+}
+```
+
+<br>

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/config.json

@@ -0,0 +1,167 @@
+{
+  "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": "base",
+  "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": {
+    },
+    "spk_is_dialect": {
+    },
+    "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"
+}

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/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
+}

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/preprocessor_config.json

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

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/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"
+}

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/speech_tokenizer/configuration.json

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

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/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
+}

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-Base/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|>"
+}

Qwen3-TTS/Qwen3-TTS-12Hz-1.7B-VoiceDesign/config.json

@@ -1,163 +1,163 @@
-{
-  "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": "voice_design",
-  "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": {
-    },
-    "spk_is_dialect": {
-    },
-    "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"
-}
+{
+  "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": "voice_design",
+  "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": {
+    },
+    "spk_is_dialect": {
+    },
+    "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"
+}

checkpoints/xl/rt_artemisLuxe_matureFLAT20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b502424e6bbfbc8d939d5d719fda9dde5748765d3399767c36226e03a28dee
+size 7105348436

checkpoints/xl/rt_perfectdeliberate_v90.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea4ec6c4d248fb9cdc3209bcbf3fccb05acb1a2a901d3f1e805e39810ed0b09
+size 6938040682

checkpoints/xl/rta_copaxTimeless_xplus2BNSFW1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066eb889380177ab1212eb485146759b876dd9cc43b33cfdc999e0f7511994c1
+size 6938040690

diffusion_models/Wan2.2/smoothMix2214BI2V_i2v_high.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e743495c4cd7c77dd97301b1fc48d86995d10ad30cad7222cdf936b9e952d7
+size 21283564107

diffusion_models/Wan2.2/smoothMix2214BI2V_i2v_low.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b746c7d05ab9c4a2d6c617cff9f660068bad125e55bbc01b7eefd175c0fad54a
+size 21283564099

diffusion_models/Wan2.2/wb_dasiwaWAN22I2V14BLightspeed_boundbite_high_V10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a51de3ec770a238d5641c261c324cb670dbdd895e05bdafbce654edc62c880f
+size 14527124344

diffusion_models/Wan2.2/wb_dasiwaWAN22I2V14BLightspeed_boundbite_low_V10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d28e3ae48a56d33a4805b1fec8b89a5451a2adab784afe25de50d076787d312
+size 14527124344

diffusion_models/cocomix/copaxTimeless_qwenUnreal_Overcooked_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c3e976b0f7e287665ee2fa807ecbd2b5d889b97ac6ae4244e10d4ff638328d
+size 40861031488

diffusion_models/zi/zp_moodyPornMix_zitV11DPO.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674f39a1b3e5201b6664284ca762b2dac9658ec6af198f61e8b4b93f0f06a5c8
+size 12309879664

diffusion_models/zi/zpw_nsfwProjectAnime_v10FP16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d88ea0f2875584f16d559952dadd283c93647a314c5e1da3c68c89f16ad70b4
+size 12309890920

omnivoice/OmniVoice/.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

omnivoice/OmniVoice/README.md

@@ -0,0 +1,785 @@
+---
+base_model:
+- Qwen/Qwen3-0.6B
+language:
+- aae
+- aal
+- aao
+- ab
+- abb
+- abn
+- abr
+- abs
+- abv
+- acm
+- acw
+- acx
+- adf
+- adx
+- ady
+- aeb
+- aec
+- af
+- afb
+- afo
+- ahl
+- ahs
+- ajg
+- aju
+- ala
+- aln
+- alo
+- am
+- amu
+- an
+- anc
+- ank
+- anp
+- anw
+- aom
+- apc
+- apd
+- arb
+- arq
+- ars
+- ary
+- arz
+- as
+- ast
+- avl
+- awo
+- ayl
+- ayp
+- az
+- ba
+- bag
+- bas
+- bax
+- bba
+- bbj
+- bbl
+- bbu
+- bce
+- bci
+- bcs
+- bcy
+- bda
+- bde
+- bdm
+- be
+- beb
+- bew
+- bfd
+- bft
+- bg
+- bgp
+- bhb
+- bhh
+- bho
+- bhp
+- bhr
+- bjj
+- bjk
+- bjn
+- bjt
+- bkh
+- bkm
+- bky
+- bmm
+- bmq
+- bn
+- bnm
+- bnn
+- bns
+- bo
+- bou
+- bqg
+- br
+- bra
+- brh
+- bri
+- brx
+- bs
+- bsh
+- bsj
+- bsk
+- btm
+- btv
+- bug
+- bum
+- buo
+- bux
+- bwr
+- bxf
+- byc
+- bys
+- byv
+- byx
+- bzc
+- bzw
+- ca
+- ccg
+- ceb
+- cen
+- cfa
+- cgg
+- chq
+- cjk
+- ckb
+- ckl
+- ckr
+- cky
+- cnh
+- cpy
+- cs
+- cte
+- ctl
+- cut
+- cux
+- cv
+- cy
+- da
+- dag
+- dar
+- dav
+- dbd
+- dcc
+- de
+- deg
+- dgh
+- dgo
+- dje
+- dmk
+- dml
+- dru
+- dty
+- dua
+- dv
+- dyu
+- dzg
+- ebr
+- ebu
+- ego
+- eiv
+- eko
+- ekr
+- el
+- elm
+- en
+- eo
+- es
+- esu
+- et
+- eto
+- ets
+- etu
+- eu
+- ewo
+- ext
+- eyo
+- fa
+- fan
+- fat
+- ff
+- ffm
+- fi
+- fia
+- fil
+- fip
+- fkk
+- fmp
+- fr
+- fub
+- fuc
+- fue
+- fuf
+- fuh
+- fui
+- fuq
+- fuv
+- fy
+- ga
+- gbm
+- gbr
+- gby
+- gcc
+- gdf
+- gej
+- ges
+- ggg
+- gid
+- gig
+- giz
+- gjk
+- gju
+- gl
+- glw
+- gn
+- gol
+- gom
+- gsl
+- gu
+- gui
+- gur
+- guz
+- gv
+- gwc
+- gwe
+- gwt
+- gya
+- gyz
+- ha
+- hah
+- hao
+- haw
+- haz
+- hbb
+- he
+- hem
+- hi
+- hia
+- hkk
+- hla
+- hno
+- hoj
+- hr
+- hsb
+- ht
+- hu
+- hue
+- hul
+- hux
+- hwo
+- hy
+- hz
+- ia
+- ibb
+- id
+- ida
+- idu
+- ig
+- ijc
+- ijn
+- ik
+- ikw
+- is
+- ish
+- iso
+- it
+- its
+- itw
+- itz
+- ja
+- jal
+- jax
+- jgo
+- jmx
+- jns
+- jqr
+- juk
+- juo
+- jv
+- ka
+- kab
+- kai
+- kaj
+- kam
+- kbd
+- kbl
+- kbt
+- kcq
+- kdh
+- kea
+- keu
+- kfe
+- kfk
+- kfp
+- khg
+- khw
+- kj
+- kjc
+- kjk
+- kk
+- kln
+- kls
+- km
+- kmr
+- kmy
+- kn
+- kna
+- knn
+- ko
+- kol
+- koo
+- kpo
+- kqo
+- ks
+- ksd
+- ksf
+- kto
+- kuh
+- kvx
+- kw
+- kwm
+- kxp
+- ky
+- kyx
+- lag
+- lb
+- lcm
+- ldb
+- lg
+- lij
+- lir
+- lkb
+- lla
+- ln
+- lnu
+- lo
+- loa
+- lrk
+- lss
+- lt
+- ltg
+- lto
+- lua
+- luo
+- lus
+- lv
+- lwg
+- mab
+- maf
+- mai
+- mau
+- max
+- mbo
+- mcf
+- mcn
+- mcx
+- mdd
+- mde
+- mdf
+- mek
+- mer
+- meu
+- mfm
+- mfn
+- mfo
+- mfv
+- mgg
+- mgi
+- mhk
+- mhr
+- mi
+- mig
+- miu
+- mk
+- mkf
+- mki
+- ml
+- mlq
+- mn
+- mne
+- mni
+- mqy
+- mr
+- mrj
+- mrr
+- mrt
+- ms
+- mse
+- msh
+- msw
+- mt
+- mtr
+- mtu
+- mtx
+- mua
+- mug
+- mui
+- mve
+- mvy
+- mxs
+- mxu
+- mxy
+- my
+- myv
+- mzl
+- nal
+- nan
+- nap
+- nb
+- nbh
+- ncf
+- nco
+- ncx
+- ndi
+- ng
+- ngi
+- nhg
+- nhi
+- nhn
+- nhq
+- nja
+- nl
+- nla
+- nlv
+- nmg
+- nmz
+- nn
+- nnh
+- 'no'
+- noe
+- npi
+- nso
+- ny
+- nyu
+- oc
+- odk
+- odu
+- ogo
+- om
+- orc
+- oru
+- ory
+- os
+- pa
+- pbs
+- pbt
+- pbu
+- pcm
+- pex
+- phl
+- phr
+- pip
+- piy
+- pko
+- pl
+- plk
+- plt
+- pmq
+- pms
+- pmy
+- pnb
+- poc
+- poe
+- pow
+- prq
+- ps
+- pst
+- pt
+- pua
+- pwn
+- qug
+- qum
+- qup
+- qur
+- qus
+- quv
+- qux
+- quy
+- qva
+- qvi
+- qvj
+- qvl
+- qwa
+- qws
+- qxa
+- qxp
+- qxt
+- qxu
+- qxw
+- rag
+- rm
+- ro
+- rob
+- rof
+- roo
+- rth
+- ru
+- rup
+- rw
+- sa
+- sah
+- sat
+- sau
+- say
+- sbn
+- sc
+- scl
+- scn
+- sd
+- sei
+- shu
+- si
+- sip
+- siw
+- sjr
+- sk
+- skg
+- skr
+- sl
+- sn
+- snc
+- snk
+- so
+- sol
+- sps
+- sq
+- sr
+- src
+- sro
+- ssi
+- ste
+- sua
+- sv
+- sva
+- sw
+- szy
+- ta
+- tan
+- tar
+- tay
+- tbf
+- tcf
+- tcy
+- tdn
+- tdx
+- te
+- tg
+- tgc
+- th
+- the
+- thq
+- thr
+- thv
+- ti
+- tig
+- tio
+- tk
+- tkg
+- tkt
+- tli
+- tlp
+- tn
+- tok
+- tpl
+- tpz
+- tqp
+- tr
+- trp
+- trq
+- trv
+- trw
+- tt
+- ttj
+- ttr
+- ttu
+- tui
+- tul
+- tuq
+- tuv
+- tuy
+- tvo
+- tvu
+- tw
+- twu
+- txs
+- txy
+- udl
+- ug
+- uk
+- uki
+- umb
+- ur
+- ush
+- uz
+- uzn
+- vai
+- var
+- ver
+- vi
+- vmc
+- vmj
+- vmm
+- vmp
+- vmz
+- vot
+- vro
+- wbl
+- wci
+- weo
+- wes
+- wja
+- wji
+- wo
+- wof
+- xh
+- xhe
+- xka
+- xmf
+- xmv
+- xmw
+- xpe
+- xti
+- xtu
+- yaq
+- yav
+- yay
+- ydd
+- ydg
+- yer
+- 'yes'
+- yi
+- yo
+- yue
+- zga
+- zgh
+- zh
+- zoc
+- zoh
+- zor
+- zpv
+- zpy
+- ztg
+- ztn
+- ztp
+- zts
+- ztu
+- zu
+- zza
+license: apache-2.0
+pipeline_tag: text-to-speech
+tags:
+- zero-shot
+- multilingual
+- voice-cloning
+- voice-design
+library_name: omnivoice
+---
+
+# OmniVoice 🌍
+
+<p align="center">
+  <img width="200" height="200" alt="OmniVoice" src="https://zhu-han.github.io/omnivoice/pics/omnivoice.jpg" />
+</p>
+
+<p align="center">
+  <a href="https://huggingface.co/k2-fsa/OmniVoice"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-FFD21E" alt="Hugging Face Model"></a>
+  &nbsp;
+  <a href="https://huggingface.co/spaces/k2-fsa/OmniVoice"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Space-blue" alt="Hugging Face Space"></a>
+  &nbsp;
+  <a href="https://huggingface.co/papers/2604.00688"><img src="https://img.shields.io/badge/arXiv-Paper-B31B1B.svg"></a>
+  &nbsp;
+  <a href="https://github.com/k2-fsa/OmniVoice"><img src="https://img.shields.io/badge/GitHub-Code-181717?logo=GitHub" alt="GitHub Code"></a>
+  &nbsp;
+  <a href="https://zhu-han.github.io/omnivoice"><img src="https://img.shields.io/badge/GitHub.io-Demo_Page-blue?logo=GitHub&style=flat-square"></a>
+  &nbsp;
+  <a href="https://colab.research.google.com/github/k2-fsa/OmniVoice/blob/master/docs/OmniVoice.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+</p>
+
+
+OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.
+
+- **Paper:** [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://huggingface.co/papers/2604.00688)
+- **Repository:** [GitHub](https://github.com/k2-fsa/OmniVoice)
+- **Demo:** [Hugging Face Space](https://huggingface.co/spaces/k2-fsa/OmniVoice)
+- **Colab:** [Google Colab Notebook](https://colab.research.google.com/github/k2-fsa/OmniVoice/blob/master/docs/OmniVoice.ipynb)
+
+## Key Features
+
+- **600+ Languages Supported**: The broadest language coverage among zero-shot TTS models.
+- **Voice Cloning**: State-of-the-art voice cloning quality from a short reference audio.
+- **Voice Design**: Control voices via assigned speaker attributes (gender, age, pitch, dialect/accent, whisper, etc.).
+- **Fine-grained Control**: Non-verbal symbols (e.g., `[laughter]`) and pronunciation correction via pinyin or phonemes.
+- **Fast Inference**: RTF as low as 0.025 (40x faster than real-time).
+- **Diffusion Language Model-style Architecture**: A clean, streamlined, and scalable design that delivers both quality and speed.
+
+## Usage
+
+To get started, install the `omnivoice` library:
+
+> We recommend using a fresh virtual environment (e.g., `conda`, `venv`, etc.) to avoid conflicts.
+
+**Step 1**: Install PyTorch
+
+<details>
+<summary>NVIDIA GPU</summary>
+
+```bash
+# Install pytorch with your CUDA version, e.g.
+pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 --extra-index-url https://download.pytorch.org/whl/cu128
+```
+> See [PyTorch official site](https://pytorch.org/get-started/locally/) for other versions installation.
+
+</details>
+
+<details>
+<summary>Apple Silicon</summary>
+
+```bash
+pip install torch==2.8.0 torchaudio==2.8.0
+```
+
+</details>
+
+**Step 2**: Install OmniVoice
+
+```bash
+pip install omnivoice
+```
+
+### Python API
+
+You can use OmniVoice for zero-shot voice cloning as follows:
+
+```python
+from omnivoice import OmniVoice
+import soundfile as sf
+import torch
+
+# Load the model
+model = OmniVoice.from_pretrained(
+    "k2-fsa/OmniVoice",
+    device_map="cuda:0",
+    dtype=torch.float16
+)
+
+# Generate audio
+audio = model.generate(
+    text="Hello, this is a test of zero-shot voice cloning.",
+    ref_audio="ref.wav",
+    ref_text="Transcription of the reference audio.",
+) # audio is a list of `np.ndarray` with shape (T,) at 24 kHz.
+
+sf.write("out.wav", audio[0], 24000)
+```
+
+For more generation modes (e.g., voice design), functions (e.g., non-verbal symbols, pronunciation correction) and comprehensive usage instructions, see our [GitHub Repository](https://github.com/k2-fsa/OmniVoice).
+
+
+## Discussion & Communication
+
+You can directly discuss on [GitHub Issues](https://github.com/k2-fsa/OmniVoice/issues).
+
+You can also scan the QR code to join our wechat group or follow our wechat official account.
+
+| Wechat Group | Wechat Official Account |
+| ------------ | ----------------------- |
+|![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_group.jpg) |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_account.jpg) |
+
+## Citation
+
+```bibtex
+@article{zhu2026omnivoice,
+      title={OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models},
+      author={Zhu, Han and Ye, Lingxuan and Kang, Wei and Yao, Zengwei and Guo, Liyong and Kuang, Fangjun and Han, Zhifeng and Zhuang, Weiji and Lin, Long and Povey, Daniel},
+      journal={arXiv preprint arXiv:2604.00688},
+      year={2026}
+}
+```
+
+
+## Disclaimer
+
+This project is intended only for academic research purposes. Users are strictly prohibited from using this model for unauthorized voice cloning, voice impersonation, fraud, scams, or any other illegal or unethical activities. All users shall ensure full compliance with applicable local laws, regulations, and ethical standards. The developers assume no liability for any misuse of this model and advocate for responsible AI development and use, encouraging the community to uphold safety and ethical principles in AI research and applications.

omnivoice/OmniVoice/audio_tokenizer/.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

omnivoice/OmniVoice/audio_tokenizer/LICENSE

@@ -0,0 +1,43 @@
+BOSON HIGGS AUDIO 2 COMMUNITY LICENSE AGREEMENT
+
+Boson Higgs Audio 2 Version Release Date: June 20, 2025
+
+This License Agreement (the “Agreement”) is entered into by and between Licensee (as defined below) and Boson AI USA, Inc. (“Boson”) and is based upon the Meta Llama 3 Community License Agreement as of April 18, 2024 (the “Meta License Agreement”), which can be found at https://llama.meta.com/llama3/license/. The terms and conditions of the Meta License Agreement are hereby incorporated herein by reference and Unless stated otherwise below, its terms apply. The Higgs Audio 2 model developed by Boson AI USA, Inc. (“Higgs Materials”) is an audio model derived from Meta Llama 3 software and algorithms. 
+
+“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Higgs Materials set forth herein and the Meta License Agreement.
+
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering into this Agreement on their behalf.
+
+“Higgs Audio 2” means the foundational large audio language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing developed by Boson AI distributed at https://github.com/boson-ai/boson-multimodal or otherwise.
+“Higgs Materials” means, collectively, Boson’s proprietary modification of Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.
+
+“Boson” or “we” means Boson AI USA, Inc.
+
+By clicking “I Accept” below or by using or distributing any portion or element of the Higgs Materials, you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution.
+a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Boson’s intellectual property or other rights owned by Boson embodied in the Higgs Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Higgs Materials.
+b. Redistribution and Use.
+i. If you distribute or make available the Higgs Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement and the of Meta License ’s Llama 3 agreement with any such Higgs Materials; and (B) prominently display “Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved and Meta Llama 3 licensed under the Meta Llama 3 Community License, Copyright Meta Platforms, Inc., All Right Reserved". based on Meta Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you use the Higgs Materials to create, modify, enhance, train, fine tune, or otherwise improve an AI model or similar software, which is distributed or made available, you shall also include “Higgs Audio 2” at the beginning of any such AI model or software name.
+ii. Even if you receive Higgs Materials, or any modifications, enhancements or derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will apply to you.
+iii. You must retain in all copies of the Llama Materials that you distribute and as set forth above, include the following attribution notice within a “Notice” text file distributed as a part of such copies: 
+“Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
+“Boson Higgs Audio 2 is licensed under the Boson Community License, Copyright © Boson AI USA, Inc. All Rights Reserved.”
+iv. Your use of the Higgs Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.
+v. You will not use the Higgs Materials or any output or results of the Higgs Materials to improve any other large language model (excluding Boson Higgs Audio 2 or derivative works thereof).
+vi. You hereby acknowledge that Boson is the owner of the Higgs Materials and under no circumstance shall you bring any legal action, claim, charge, demand challenging such ownership rights of Boson.
+
+2. Additional Commercial Terms. If the annual active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 100,000 annual active users in the preceding calendar year, you must request an expanded license from Boson AI, which Boson AI may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Boson AI otherwise expressly grants you such rights.
+
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE Higgs Materials AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITH ALL FAULTS, WITHOUT WARRANTIES OF ANY KIND EXPRESS, IMPLIED, BASED UPON CUSTOM AND USAGE OR COURSE OF DEALING, AND BOSON AI DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE HIGGS MATERIALS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR USE OF THE HIGGS MATERIALS AND ANY OUTPUT AND RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL BOSON AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF BOSON, META  OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+
+5. Intellectual Property.
+a. No trademark licenses are granted under this Agreement, or in connection with the Higgs Materials.,  nNeither Boson nor Licensee may use any name or mark owned by, or associated with, the other party hereto or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Higgs Materials or as set forth in this Section 5(a). Boson hereby grants you a license to use “Higgs Audio 2” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. All goodwill arising out of your use of the Mark will inure to the benefit of Meta and Boson AI.
+b. Subject to Boson’s ownership of the Higgs Materials and derivatives made by or for Boson AI, with respect to any derivative works and modifications of the Higgs Materials that are made by you, as between you and Boson AI, you are and will be the owner of such derivative works and modifications.
+c. If you institute litigation or other proceedings against Boson AI, Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Higgs Materials or Boson Higgs Audio 2 outputs or results, or any portion thereof any of the foregoing, constitutes infringement of the intellectual property or other rights owned or licensable by you, then any licenses granted to you hereunder this Agreement shall immediately terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Boson AI from and against any claim, charge, demand, cause of action by any third party arising out of or related to your use or distribution of the Higgs Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Higgs Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Boson AI may terminate this Agreement if you are in breach of any term or condition of this Agreement by providing you with written notice. Upon your receipt of written notice of termination of this Agreement, you shall delete the Higgs Materials from any computer, server or IT device and cease use of the Higgs Materials in all respects. Sections 1(b)(vi), 3, 4 and 7 shall survive the termination of this Agreement.
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The federal courts in the Northern District of California and the state courts in Santa Clara County, California shall have exclusive jurisdiction of any dispute arising out of this Agreement.

omnivoice/OmniVoice/audio_tokenizer/README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

omnivoice/OmniVoice/audio_tokenizer/config.json

@@ -0,0 +1,129 @@
+{
+  "acoustic_model_config": {
+    "codebook_dim": 8,
+    "codebook_loss_weight": 1.0,
+    "codebook_size": 1024,
+    "commitment_loss_weight": 0.25,
+    "decoder_hidden_size": 1024,
+    "downsampling_ratios": [
+      8,
+      5,
+      4,
+      2,
+      3
+    ],
+    "encoder_hidden_size": 64,
+    "hidden_size": 256,
+    "hop_length": 960,
+    "model_type": "dac",
+    "n_codebooks": 9,
+    "quantizer_dropout": 0,
+    "sampling_rate": 16000,
+    "upsampling_ratios": [
+      8,
+      5,
+      4,
+      2,
+      3
+    ]
+  },
+  "architectures": [
+    "HiggsAudioV2TokenizerModel"
+  ],
+  "block_dilations": [
+    1,
+    1
+  ],
+  "channel_ratios": [
+    1,
+    1
+  ],
+  "codebook_dim": 64,
+  "codebook_size": 1024,
+  "downsample_factor": 320,
+  "dtype": "float32",
+  "initializer_range": 0.02,
+  "kernel_size": 3,
+  "model_type": "higgs_audio_v2_tokenizer",
+  "sample_rate": 24000,
+  "semantic_model_config": {
+    "activation_dropout": 0.1,
+    "apply_spec_augment": true,
+    "attention_dropout": 0.1,
+    "bos_token_id": 1,
+    "classifier_proj_size": 256,
+    "conv_bias": false,
+    "conv_dim": [
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512
+    ],
+    "conv_kernel": [
+      10,
+      3,
+      3,
+      3,
+      3,
+      2,
+      2
+    ],
+    "conv_pos_batch_norm": false,
+    "conv_stride": [
+      5,
+      2,
+      2,
+      2,
+      2,
+      2,
+      2
+    ],
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "do_stable_layer_norm": false,
+    "eos_token_id": 2,
+    "feat_extract_activation": "gelu",
+    "feat_extract_norm": "group",
+    "feat_proj_dropout": 0.0,
+    "feat_proj_layer_norm": true,
+    "final_dropout": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.1,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.0,
+    "model_type": "hubert",
+    "num_attention_heads": 12,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_feat_extract_layers": 7,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32
+  },
+  "semantic_sample_rate": 16000,
+  "strides": [
+    1,
+    1
+  ],
+  "target_bandwidths": [
+    0.5,
+    1,
+    1.5,
+    2
+  ],
+  "transformers_version": "5.3.0.dev0",
+  "unit_kernel_size": 3
+}

omnivoice/OmniVoice/audio_tokenizer/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "feature_extractor_type": "DacFeatureExtractor",
+  "feature_size": 1,
+  "hop_length": 960,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 24000
+}

omnivoice/OmniVoice/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

omnivoice/OmniVoice/config.json

@@ -0,0 +1,101 @@
+{
+  "architectures": [
+    "OmniVoice"
+  ],
+  "audio_codebook_weights": [
+    8,
+    8,
+    6,
+    6,
+    4,
+    4,
+    2,
+    2
+  ],
+  "audio_mask_id": 1024,
+  "audio_vocab_size": 1025,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "llm_config": {
+    "_name_or_path": "",
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 40960,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": null,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151676
+  },
+  "model_type": "omnivoice",
+  "num_audio_codebook": 8,
+  "pad_token_id": 151643,
+  "transformers_version": "5.3.0"
+}

omnivoice/OmniVoice/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408f669b7e2b045fdf54201d815bd364e6667dbd845115da81239c40bc6dcfd1
+size 11423986

omnivoice/OmniVoice/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|denoise|>",
+    "<|lang_start|>",
+    "<|lang_end|>",
+    "<|instruct_start|>",
+    "<|instruct_end|>",
+    "<|text_start|>",
+    "<|text_end|>"
+  ],
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}