Qwen3-ForcedAligner

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+qwen3-asr-0.6b-f16/qwen3-asr-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-forced-aligner-0.6b-f16/qwen3-forced-aligner-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-forced-aligner-0.6b-q4-k-m/qwen3-forced-aligner-0.6b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-forced-aligner-0.6b-q5-k-m/qwen3-forced-aligner-0.6b-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-forced-aligner-0.6b-q8-0/qwen3-forced-aligner-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3-ForcedAligner-0.6B/.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-ForcedAligner-0.6B/README.md

@@ -0,0 +1,1393 @@
+---
+license: apache-2.0
+pipeline_tag: automatic-speech-recognition
+---
+
+# Qwen3-ASR
+
+## Overview
+
+### Introduction
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/qwen3_asr_introduction.png" width="90%"/>
+<p>
+
+The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. Experiments show that the 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs. Here are the main features:
+
+* **All-in-one**: Qwen3-ASR-1.7B and Qwen3-ASR-0.6B support language identification and speech recognition for 30 languages and 22 Chinese dialects, so as to English accents from multiple countries and regions.
+
+* **Excellent and Fast**: The Qwen3-ASR family ASR models maintains high-quality and robust recognition under complex acoustic environments and challenging text patterns. Qwen3-ASR-1.7B achieves strong performance on both open-sourced and internal benchmarks. While the 0.6B version achieves accuracy-efficient trade-off, it reaches 2000 times throughput at a concurrency of 128. They both achieve streaming / offline unified inference with single model and support transcribe long audio.
+
+* **Novel and strong forced alignment Solution**: We introduce Qwen3-ForcedAligner-0.6B, which supports timestamp prediction for arbitrary units within up to 5 minutes of speech in 11 languages. Evaluations show its timestamp accuracy surpasses E2E based forced-alignment models.
+
+* **Comprehensive inference toolkit**: In addition to open-sourcing the architectures and weights of the Qwen3-ASR series, we also release a powerful, full-featured inference framework that supports vLLM-based batch inference, asynchronous serving, streaming inference, timestamp prediction, and more.
+
+### Model Architecture
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/overview.jpg" width="100%"/>
+<p>
+
+
+### Released Models Description and Download
+
+Below is an introduction and download information for the Qwen3-ASR models. Please select and download the model that fits your needs.
+
+| Model | Supported Languages | Supported Dialects | Inference Mode | Audio Types |
+|---|---|---|---|---|
+| Qwen3-ASR-1.7B & Qwen3-ASR-0.6B | Chinese (zh), English (en), Cantonese (yue), Arabic (ar), German (de), French (fr), Spanish (es), Portuguese (pt), Indonesian (id), Italian (it), Korean (ko), Russian (ru), Thai (th), Vietnamese (vi), Japanese (ja), Turkish (tr), Hindi (hi), Malay (ms), Dutch (nl), Swedish (sv), Danish (da), Finnish (fi), Polish (pl), Czech (cs), Filipino (fil), Persian (fa), Greek (el), Hungarian (hu), Macedonian (mk), Romanian (ro) | Anhui, Dongbei, Fujian, Gansu, Guizhou, Hebei, Henan, Hubei, Hunan, Jiangxi, Ningxia, Shandong, Shaanxi, Shanxi, Sichuan, Tianjin, Yunnan, Zhejiang, Cantonese (Hong Kong accent), Cantonese (Guangdong accent), Wu language, Minnan language. | Offline / Streaming | Speech, Singing Voice, Songs with BGM |
+| Qwen3-ForcedAligner-0.6B | Chinese, English, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish | -- | NAR | Speech |
+
+During model loading in the `qwen-asr` package or vLLM, model weights will be downloaded automatically based on the model name. However, if your runtime environment does not allow downloading weights during execution, you can use 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-ASR-1.7B  --local_dir ./Qwen3-ASR-1.7B
+modelscope download --model Qwen/Qwen3-ASR-0.6B --local_dir ./Qwen3-ASR-0.6B
+modelscope download --model Qwen/Qwen3-ForcedAligner-0.6B --local_dir ./Qwen3-ForcedAligner-0.6B
+# Download through Hugging Face
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download Qwen/Qwen3-ASR-1.7B --local-dir ./Qwen3-ASR-1.7B
+huggingface-cli download Qwen/Qwen3-ASR-0.6B --local-dir ./Qwen3-ASR-0.6B
+huggingface-cli download Qwen/Qwen3-ForcedAligner-0.6B --local-dir ./Qwen3-ForcedAligner-0.6B
+```
+
+
+## Quickstart
+
+### Environment Setup
+
+The easiest way to use Qwen3-ASR is to install the `qwen-asr` Python package from PyPI. This will pull in the required runtime dependencies and allow you to load any released Qwen3-ASR model. If you’d like to simplify environment setup further, you can also use our official [Docker image](#docker). The `qwen-asr` package provides two backends: the transformers backend and the vLLM backend. For usage instructions for different backends, please refer to [Python Package Usage](#python-package-usage). 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-asr python=3.12 -y
+conda activate qwen3-asr
+```
+
+Run the following command to get the minimal installation with transformers-backend support:
+
+```bash
+pip install -U qwen-asr
+```
+
+To enable the vLLM backend for faster inference and streaming support, run:
+
+```bash
+pip install -U qwen-asr[vllm]
+```
+
+If you want to develop or modify the code locally, install from source in editable mode:
+
+```bash
+git clone https://github.com/QwenLM/Qwen3-ASR.git
+cd Qwen3-ASR
+pip install -e .
+# support vLLM backend
+# pip install -e ".[vllm]"
+```
+
+Additionally, we recommend using FlashAttention 2 to reduce GPU memory usage and accelerate inference speed, especially for long inputs and large batch sizes.
+
+```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
+
+#### Quick Inference
+
+The `qwen-asr` package provides two backends: **transformers backend** and **vLLM backend**. You can pass audio inputs as a local path, a URL, base64 data, or a `(np.ndarray, sr)` tuple, and run batch inference. To quickly try Qwen3-ASR, you can use `Qwen3ASRModel.from_pretrained(...)` for the transformers backend with the following code:
+
+```python
+import torch
+from qwen_asr import Qwen3ASRModel
+
+model = Qwen3ASRModel.from_pretrained(
+    "Qwen/Qwen3-ASR-1.7B",
+    dtype=torch.bfloat16,
+    device_map="cuda:0",
+    # attn_implementation="flash_attention_2",
+    max_inference_batch_size=32, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
+    max_new_tokens=256, # Maximum number of tokens to generate. Set a larger value for long audio input.
+)
+
+results = model.transcribe(
+    audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
+    language=None, # set "English" to force the language
+)
+
+print(results[0].language)
+print(results[0].text)
+```
+
+If you want to return timestamps, pass `forced_aligner` and its init kwargs. Here is an example of batch inference with timestamps output:
+
+```python
+import torch
+from qwen_asr import Qwen3ASRModel
+
+model = Qwen3ASRModel.from_pretrained(
+    "Qwen/Qwen3-ASR-1.7B",
+    dtype=torch.bfloat16,
+    device_map="cuda:0",
+    # attn_implementation="flash_attention_2",
+    max_inference_batch_size=32, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
+    max_new_tokens=256, # Maximum number of tokens to generate. Set a larger value for long audio input.
+    forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
+    forced_aligner_kwargs=dict(
+        dtype=torch.bfloat16,
+        device_map="cuda:0",
+        # attn_implementation="flash_attention_2",
+    ),
+)
+
+results = model.transcribe(
+    audio=[
+      "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
+      "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
+    ],
+    language=["Chinese", "English"], # can also be set to None for automatic language detection
+    return_time_stamps=True,
+)
+
+for r in results:
+    print(r.language, r.text, r.time_stamps[0])
+```
+
+For more detailed usage examples, please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_transformers.py) for the transformers backend.
+
+#### vLLM Backend
+
+If you want the fastest inference speed with Qwen3-ASR, we strongly recommend using the vLLM backend by initializing the model with `Qwen3ASRModel.LLM(...)`. Example code is provided below. Note that you must install it via `pip install -U qwen-asr[vllm]`. If you want the model to output timestamps, it’s best to install FlashAttention via `pip install -U flash-attn --no-build-isolation` to speed up inference for the forced aligner model. Remember to wrap your code under `if __name__ == '__main__':` to avoid the `spawn` error described in [vLLM Troubleshooting](https://docs.vllm.ai/en/latest/usage/troubleshooting/#python-multiprocessing).
+
+```python
+import torch
+from qwen_asr import Qwen3ASRModel
+
+if __name__ == '__main__':
+    model = Qwen3ASRModel.LLM(
+        model="Qwen/Qwen3-ASR-1.7B",
+        gpu_memory_utilization=0.7,
+        max_inference_batch_size=128, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
+        max_new_tokens=4096, # Maximum number of tokens to generate. Set a larger value for long audio input.
+        forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
+        forced_aligner_kwargs=dict(
+            dtype=torch.bfloat16,
+            device_map="cuda:0",
+            # attn_implementation="flash_attention_2",
+        ),
+    )
+
+    results = model.transcribe(
+        audio=[
+        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
+        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
+        ],
+        language=["Chinese", "English"], # can also be set to None for automatic language detection
+        return_time_stamps=True,
+    )
+
+    for r in results:
+        print(r.language, r.text, r.time_stamps[0])
+```
+
+For more detailed usage examples, please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_vllm.py) for the vLLM backend. In addition, you can start a vLLM server via the `qwen-asr-serve` command, which is a wrapper around `vllm serve`. You can pass any arguments supported by `vllm serve`, for example:
+
+```bash
+qwen-asr-serve Qwen/Qwen3-ASR-1.7B --gpu-memory-utilization 0.8 --host 0.0.0.0 --port 8000
+```
+
+And send requests to the server via:
+
+```python
+import requests
+
+url = "http://localhost:8000/v1/chat/completions"
+headers = {"Content-Type": "application/json"}
+
+data = {
+    "messages": [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio_url",
+                    "audio_url": {
+                        "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
+                    },
+                }
+            ],
+        }
+    ]
+}
+
+response = requests.post(url, headers=headers, json=data, timeout=300)
+response.raise_for_status()
+content = response.json()['choices'][0]['message']['content']
+print(content)
+
+# parse ASR output if you want
+from qwen_asr import parse_asr_output
+language, text = parse_asr_output(content)
+print(language)
+print(text)
+```
+
+#### Streaming Inference
+
+Qwen3-ASR fully supports streaming inference. Currently, streaming inference is only available with the vLLM backend. Note that streaming inference does not support batch inference or returning timestamps. Please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_vllm_streaming.py) for details. You can also launch a streaming web demo through the [guide](#streaming-demo) to experience Qwen3-ASR’s streaming transcription capabilities. 
+
+#### ForcedAligner Usage
+
+`Qwen3-ForcedAligner-0.6B` can align text–speech pairs and return word or character level timestamps. Here is an example of using the forced aligner directly:
+
+```python
+import torch
+from qwen_asr import Qwen3ForcedAligner
+
+model = Qwen3ForcedAligner.from_pretrained(
+    "Qwen/Qwen3-ForcedAligner-0.6B",
+    dtype=torch.bfloat16,
+    device_map="cuda:0",
+    # attn_implementation="flash_attention_2",
+)
+
+results = model.align(
+    audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
+    text="甚至出现交易几乎停滞的情况。",
+    language="Chinese",
+)
+
+print(results[0])
+print(results[0][0].text, results[0][0].start_time, results[0][0].end_time)
+```
+
+In addition, the forced aligner supports local paths / URLs / base64 data / `(np.ndarray, sr)` inputs and batch inference. Please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_forced_aligner.py) for details.
+
+### DashScope API Usage
+
+To further explore Qwen3-ASR, 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-ASR. | [https://help.aliyun.com/zh/model-studio/qwen-real-time-speech-recognition](https://help.aliyun.com/zh/model-studio/qwen-real-time-speech-recognition) | [https://www.alibabacloud.com/help/en/model-studio/qwen-real-time-speech-recognition](https://www.alibabacloud.com/help/en/model-studio/qwen-real-time-speech-recognition) |
+| FileTrans API for Qwen3-ASR. | [https://help.aliyun.com/zh/model-studio/qwen-speech-recognition](https://help.aliyun.com/zh/model-studio/qwen-speech-recognition) | [https://www.alibabacloud.com/help/en/model-studio/qwen-speech-recognition](https://www.alibabacloud.com/help/en/model-studio/qwen-speech-recognition) |
+
+
+## Launch Local Web UI Demo
+
+### Gradio Demo
+
+To launch the Qwen3-ASR web UI gradio demo, install the `qwen-asr` package and run `qwen-asr-demo`. Use the command below for help:
+
+```bash
+qwen-asr-demo --help
+```
+
+To launch the demo, you can use the following commands:
+
+```bash
+# Transformers backend
+qwen-asr-demo \
+  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
+  --backend transformers \
+  --cuda-visible-devices 0 \
+  --ip 0.0.0.0 --port 8000
+
+# Transformers backend + Forced Aligner (enable timestamps)
+qwen-asr-demo \
+  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
+  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
+  --backend transformers \
+  --cuda-visible-devices 0 \
+  --backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16","max_inference_batch_size":8,"max_new_tokens":256}' \
+  --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
+  --ip 0.0.0.0 --port 8000
+
+# vLLM backend + Forced Aligner (enable timestamps)
+qwen-asr-demo \
+  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
+  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
+  --backend vllm \
+  --cuda-visible-devices 0 \
+  --backend-kwargs '{"gpu_memory_utilization":0.7,"max_inference_batch_size":8,"max_new_tokens":2048}' \
+  --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
+  --ip 0.0.0.0 --port 8000
+```
+
+Then open `http://<your-ip>:8000`, or access it via port forwarding in tools like VS Code.
+
+#### Backend Notes
+
+This demo supports two backends: transformers and vLLM. All backend-specific initialization parameters should be passed via `--backend-kwargs` as a JSON dict. If not provided, the demo will use sensible defaults.
+
+```bash
+# Example: override transformers init args without flash attention
+--backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}'
+
+# Example: override vLLM init args with 65% GPU memory
+--backend-kwargs '{"gpu_memory_utilization":0.65}'
+```
+
+#### CUDA Device Notes
+
+Because vLLM does not follow `cuda:0` style device selection, this demo selects GPUs by setting `CUDA_VISIBLE_DEVICES` via `--cuda-visible-devices`.
+
+```bash
+# Use GPU 0
+--cuda-visible-devices 0
+
+# Use GPU 1
+--cuda-visible-devices 1
+```
+
+#### Timestamps Notes
+
+Timestamps are only available when `--aligner-checkpoint` is provided. If you launch the demo without a forced aligner, the timestamps UI will be hidden automatically.
+
+```bash
+# No forced aligner
+qwen-asr-demo --asr-checkpoint Qwen/Qwen3-ASR-1.7B
+
+# With forced aligner
+qwen-asr-demo \
+  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
+  --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B
+```
+
+#### HTTPS Notes
+
+To avoid browser microphone permission issues after deploying the server, 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, generate a private key and a self-signed certificate (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-asr-demo \
+  --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
+  --backend transformers \
+  --cuda-visible-devices 0 \
+  --ip 0.0.0.0 --port 8000 \
+  --ssl-certfile cert.pem \
+  --ssl-keyfile key.pem \
+  --no-ssl-verify
+```
+
+Then open `https://<your-ip>:8000` to use it. If your browser shows a warning, that’s expected for self-signed certificates. For production, use a real certificate.
+
+### Streaming Demo
+
+To experience Qwen3-ASR’s streaming transcription capability in a web UI, we provide a minimal Flask-based streaming demo. The demo captures microphone audio in the browser, resamples it to 16,000 Hz, and continuously pushes PCM chunks to the model. Run the demo with the following command:
+
+```bash
+qwen-asr-demo-streaming \
+  --asr-model-path Qwen/Qwen3-ASR-1.7B \
+  --host 0.0.0.0 \
+  --port 8000 \
+  --gpu-memory-utilization 0.9
+```
+
+Then open `http://<your-ip>:8000`, or access it via port forwarding in tools like VS Code.
+
+## Deployment with vLLM
+
+vLLM officially provides day-0 model support for Qwen3-ASR for efficient inference. 
+
+### Installation
+You can run Qwen3-ASR with vLLM nightly wheel or docker image. To install the nightly version of vLLM, we recommend using `uv` as the environment manager
+```bash
+uv venv
+source .venv/bin/activate
+uv pip install -U vllm --pre \
+    --extra-index-url https://wheels.vllm.ai/nightly/cu129 \
+    --extra-index-url https://download.pytorch.org/whl/cu129 \
+    --index-strategy unsafe-best-match
+uv pip install "vllm[audio]" # For additional audio dependencies
+```
+
+### Online Serving
+You can easily deploy Qwen3-ASR with vLLM by running the following command
+```bash
+vllm serve Qwen/Qwen3-ASR-1.7B
+```
+After the model server is successfully deployed, you can interact with it in multiple ways.
+
+#### Using OpenAI SDK
+```python
+import base64
+import httpx
+from openai import OpenAI
+
+# Initialize client
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="EMPTY"
+)
+
+# Create multimodal chat completion request
+response = client.chat.completions.create(
+    model="Qwen/Qwen3-ASR-1.7B",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio_url",
+                    "audio_url": {
+                        {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}
+                    }
+                }
+            ]
+        }
+    ],
+)
+
+print(response.choices[0].message.content)
+```
+This model is also supported on vLLM with OpenAI transcription API.
+```python
+import httpx
+from openai import OpenAI
+
+# Initialize client
+client = OpenAI(
+    base_url="http://localhost:8000/v1",
+    api_key="EMPTY"
+)
+audio_url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
+audio_file = httpx.get(audio_url).content
+
+transcription = client.audio.transcriptions.create(
+    model="Qwen/Qwen3-ASR-1.7B",
+    file=audio_file,
+)
+
+print(transcription.text)
+```
+
+#### Using cURL
+```bash
+curl http://localhost:8000/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+    "messages": [
+    {"role": "user", "content": [
+        {"type": "audio_url", "audio_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}}
+    ]}
+    ]
+    }'
+```
+
+### Offline Inference
+See the following example on using vLLM to run offline inference with Qwen3-ASR
+```python
+from vllm import LLM, SamplingParams
+from vllm.assets.audio import AudioAsset
+import base64
+import requests
+
+# Initialize the LLM
+llm = LLM(
+    model="Qwen/Qwen3-ASR-1.7B"
+)
+
+# Load audio
+audio_asset = AudioAsset("winning_call")
+
+# Create conversation with audio content
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "audio_url",
+                "audio_url": {"url": audio_asset.url}
+            }
+        ]
+    }
+]
+
+sampling_params = SamplingParams(temperature=0.01, max_tokens=256)
+
+# Run inference using .chat()
+outputs = llm.chat(conversation, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+```
+
+
+## Docker
+
+To make it easier to use our `qwen-asr` Python package, we provide a pre-built Docker image: [qwenllm/qwen3-asr](https://hub.docker.com/r/qwenllm/qwen3-asr). You only need to install the GPU driver and download the model files to run the code. Please follow the [NVIDIA Container Toolkit installation guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) to ensure Docker can access your GPU. If you are in Mainland China and have trouble reaching Docker Hub, you may use a registry mirror to accelerate image pulls.
+
+First, pull the image and start a container:
+
+```bash
+LOCAL_WORKDIR=/path/to/your/workspace
+HOST_PORT=8000
+CONTAINER_PORT=80
+docker run --gpus all --name qwen3-asr \
+    -v /var/run/docker.sock:/var/run/docker.sock -p $HOST_PORT:$CONTAINER_PORT \
+    --mount type=bind,source=$LOCAL_WORKDIR,target=/data/shared/Qwen3-ASR \
+    --shm-size=4gb \
+    -it qwenllm/qwen3-asr:latest
+```
+
+After running the command, you will enter the container’s bash shell. Your local workspace (**replace** `/path/to/your/workspace` **with the actual path**) will be mounted inside the container at `/data/shared/Qwen3-ASR`. Port `8000` on the host is mapped to port `80` in the container, so you can access services running in the container via `http://<host-ip>:8000`. Note that services inside the container must bind to `0.0.0.0` (not `127.0.0.1`) for port forwarding to work.
+
+If you exit the container, you can start it again and re-enter it with:
+
+```bash
+docker start qwen3-asr
+docker exec -it qwen3-asr bash
+```
+
+To remove the container completely, run:
+
+```bash
+docker rm -f qwen3-asr
+```
+
+
+## Evaluation
+
+During evaluation, we ran inference for all models with `dtype=torch.bfloat16` and set `max_new_tokens=1024` using vLLM. Greedy search was used for all decoding, and none of the tests specified a language parameter. The detailed evaluation results are shown below.
+
+<details>
+<summary>ASR Benchmarks on Public Datasets (WER ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th colspan="2" style="text-align: left;"></th>
+      <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
+      <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
+      <th style="text-align: center;">Doubao-ASR</th>
+      <th style="text-align: center;">Whisper<br>-large-v3</th>
+      <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">English (en)</td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">Librispeech<br>clean | other</td>
+      <td style="text-align: center;"><strong>1.39</strong> | 3.75</td>
+      <td style="text-align: center;">2.89 | 3.56</td>
+      <td style="text-align: center;">2.78 | 5.70</td>
+      <td style="text-align: center;">1.51 | 3.97</td>
+      <td style="text-align: center;">1.68 | 4.03</td>
+      <td style="text-align: center;">2.11 | 4.55</td>
+      <td style="text-align: center;">1.63 | <strong>3.38</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">GigaSpeech</td>
+      <td style="text-align: center;">25.50</td>
+      <td style="text-align: center;">9.37</td>
+      <td style="text-align: center;">9.55</td>
+      <td style="text-align: center;">9.76</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">8.88</td>
+      <td style="text-align: center;"><strong>8.45</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">CV-en</td>
+      <td style="text-align: center;">9.08</td>
+      <td style="text-align: center;">14.49</td>
+      <td style="text-align: center;">13.78</td>
+      <td style="text-align: center;">9.90</td>
+      <td style="text-align: center;">9.90</td>
+      <td style="text-align: center;">9.92</td>
+      <td style="text-align: center;"><strong>7.39</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">Fleurs-en</td>
+      <td style="text-align: center;"><strong>2.40</strong></td>
+      <td style="text-align: center;">2.94</td>
+      <td style="text-align: center;">6.31</td>
+      <td style="text-align: center;">4.08</td>
+      <td style="text-align: center;">5.49</td>
+      <td style="text-align: center;">4.39</td>
+      <td style="text-align: center;">3.35</td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">MLS-en</td>
+      <td style="text-align: center;">5.12</td>
+      <td style="text-align: center;"><strong>3.68</strong></td>
+      <td style="text-align: center;">7.09</td>
+      <td style="text-align: center;">4.87</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">6.00</td>
+      <td style="text-align: center;">4.58</td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">Tedlium</td>
+      <td style="text-align: center;">7.69</td>
+      <td style="text-align: center;">6.15</td>
+      <td style="text-align: center;">4.91</td>
+      <td style="text-align: center;">6.84</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>3.85<strong></td>
+      <td style="text-align: center;"><strong>4.50</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">VoxPopuli</td>
+      <td style="text-align: center;">10.29</td>
+      <td style="text-align: center;">11.36</td>
+      <td style="text-align: center;">12.12</td>
+      <td style="text-align: center;">12.05</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>9.96<strong></td>
+      <td style="text-align: center;"><strong>9.15</strong></td>
+    </tr>
+    <tr>
+      <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese (zh)</td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">WenetSpeech<br>net | meeting</td>
+      <td style="text-align: center;">15.30 | 32.27</td>
+      <td style="text-align: center;">14.43 | 13.47</td>
+      <td style="text-align: center;">N/A</td>
+      <td style="text-align: center;">9.86 | 19.11</td>
+      <td style="text-align: center;">6.35 | -</td>
+      <td style="text-align: center;">5.97 | 6.88</td>
+      <td style="text-align: center;"><strong>4.97</strong> | <strong>5.88</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">AISHELL-2-test</td>
+      <td style="text-align: center;">4.24</td>
+      <td style="text-align: center;">11.62</td>
+      <td style="text-align: center;">2.85</td>
+      <td style="text-align: center;">5.06</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">3.15</td>
+      <td style="text-align: center;"><strong>2.71</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">SpeechIO</td>
+      <td style="text-align: center;">12.86</td>
+      <td style="text-align: center;">5.30</td>
+      <td style="text-align: center;">2.93</td>
+      <td style="text-align: center;">7.56</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">3.44</td>
+      <td style="text-align: center;"><strong>2.88</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">Fleurs-zh</td>
+      <td style="text-align: center;">2.44</td>
+      <td style="text-align: center;">2.71</td>
+      <td style="text-align: center;">2.69</td>
+      <td style="text-align: center;">4.09</td>
+      <td style="text-align: center;">3.51</td>
+      <td style="text-align: center;">2.88</td>
+      <td style="text-align: center;"><strong>2.41</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">CV-zh</td>
+      <td style="text-align: center;">6.32</td>
+      <td style="text-align: center;">7.70</td>
+      <td style="text-align: center;">5.95</td>
+      <td style="text-align: center;">12.91</td>
+      <td style="text-align: center;">6.20</td>
+      <td style="text-align: center;">6.89</td>
+      <td style="text-align: center;"><strong>5.35</strong></td>
+    </tr>
+    <tr>
+      <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Dialect</td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">KeSpeech</td>
+      <td style="text-align: center;">26.87</td>
+      <td style="text-align: center;">24.71</td>
+      <td style="text-align: center;">5.27</td>
+      <td style="text-align: center;">28.79</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">7.08</td>
+      <td style="text-align: center;"><strong>5.10</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">Fleurs-yue</td>
+      <td style="text-align: center;">4.98</td>
+      <td style="text-align: center;">9.43</td>
+      <td style="text-align: center;">4.98</td>
+      <td style="text-align: center;">9.18</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">5.79</td>
+      <td style="text-align: center;"><strong>3.98</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">CV-yue</td>
+      <td style="text-align: center;">11.36</td>
+      <td style="text-align: center;">18.76</td>
+      <td style="text-align: center;">13.20</td>
+      <td style="text-align: center;">16.23</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">9.50</td>
+      <td style="text-align: center;"><strong>7.57</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">CV-zh-tw</td>
+      <td style="text-align: center;">6.32</td>
+      <td style="text-align: center;">7.31</td>
+      <td style="text-align: center;">4.06</td>
+      <td style="text-align: center;">7.84</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">5.59</td>
+      <td style="text-align: center;"><strong>3.77</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">WenetSpeech-Yue<br>short | long</td>
+      <td style="text-align: center;">15.62 | 25.29</td>
+      <td style="text-align: center;">25.19 | 11.23</td>
+      <td style="text-align: center;">9.74 | 11.40</td>
+      <td style="text-align: center;">32.26 | 46.64</td>
+      <td style="text-align: center;">- | -</td>
+      <td style="text-align: center;">7.54 | 9.92</td>
+      <td style="text-align: center;"><strong>5.82</strong> | <strong>8.85</strong></td>
+    </tr>
+    <tr>
+      <td colspan="2" style="text-align: left;">WenetSpeech-Chuan<br>easy | hard</td>
+      <td style="text-align: center;">34.81 | 53.98</td>
+      <td style="text-align: center;">43.79 | 67.30</td>
+      <td style="text-align: center;"><strong>11.40<strong> | <strong>20.20</strong></td>
+      <td style="text-align: center;">14.35 | 26.80</td>
+      <td style="text-align: center;">- | -</td>
+      <td style="text-align: center;">13.92 | 24.45</td>
+      <td style="text-align: center;">11.99 | 21.63</td>
+    </tr>
+  </tbody>
+</table>
+
+</details>
+
+<details>
+<summary>ASR Benchmarks on Internal Datasets (WER ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;"></th>
+      <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
+      <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
+      <th style="text-align: center;">Doubao-ASR</th>
+      <th style="text-align: center;">Whisper<br>-large-v3</th>
+      <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Accented English</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Dialog-Accented English</td>
+      <td style="text-align: center;">28.56</td>
+      <td style="text-align: center;">23.85</td>
+      <td style="text-align: center;">20.41</td>
+      <td style="text-align: center;">21.30</td>
+      <td style="text-align: center;">19.96</td>
+      <td style="text-align: center;"><strong>16.62<strong></td>
+      <td style="text-align: center;"><strong>16.07</strong></td>
+    </tr>
+    <tr>
+      <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Mandarin</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Elders&Kids</td>
+      <td style="text-align: center;">14.27</td>
+      <td style="text-align: center;">36.93</td>
+      <td style="text-align: center;">4.17</td>
+      <td style="text-align: center;">10.61</td>
+      <td style="text-align: center;">4.54</td>
+      <td style="text-align: center;">4.48</td>
+      <td style="text-align: center;"><strong>3.81</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">ExtremeNoise</td>
+      <td style="text-align: center;">36.11</td>
+      <td style="text-align: center;">29.06</td>
+      <td style="text-align: center;">17.04</td>
+      <td style="text-align: center;">63.17</td>
+      <td style="text-align: center;">36.55</td>
+      <td style="text-align: center;">17.88</td>
+      <td style="text-align: center;"><strong>16.17</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">TongueTwister</td>
+      <td style="text-align: center;">20.87</td>
+      <td style="text-align: center;">4.97</td>
+      <td style="text-align: center;">3.47</td>
+      <td style="text-align: center;">16.63</td>
+      <td style="text-align: center;">9.02</td>
+      <td style="text-align: center;">4.06</td>
+      <td style="text-align: center;"><strong>2.44</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Dialog-Mandarin</td>
+      <td style="text-align: center;">20.73</td>
+      <td style="text-align: center;">12.50</td>
+      <td style="text-align: center;">6.61</td>
+      <td style="text-align: center;">14.01</td>
+      <td style="text-align: center;">7.32</td>
+      <td style="text-align: center;">7.06</td>
+      <td style="text-align: center;"><strong>6.54</strong></td>
+    </tr>
+    <tr>
+      <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Dialect</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Dialog-Cantonese</td>
+      <td style="text-align: center;">16.05</td>
+      <td style="text-align: center;">14.98</td>
+      <td style="text-align: center;">7.56</td>
+      <td style="text-align: center;">31.04</td>
+      <td style="text-align: center;">5.85</td>
+      <td style="text-align: center;"><strong>4.80<strong></td>
+      <td style="text-align: center;"><strong>4.12</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Dialog-Chinese Dialects</td>
+      <td style="text-align: center;">45.37</td>
+      <td style="text-align: center;">47.70</td>
+      <td style="text-align: center;">19.85</td>
+      <td style="text-align: center;">44.55</td>
+      <td style="text-align: center;">19.41</td>
+      <td style="text-align: center;"><strong>18.24<strong></td>
+      <td style="text-align: center;"><strong>15.94</strong></td>
+    </tr>
+  </tbody>
+</table>
+<p><strong>Dialect coverage:</strong> Results for <em>Dialog-Accented English</em> are averaged over 16 accents, and results for <em>Dialog-Chinese Dialects</em> are averaged over 22 Chinese dialects.</p>
+
+</details>
+
+<details>
+<summary>Multilingual ASR Benchmarks (WER ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;"></th>
+      <th style="text-align: center;">GLM-ASR<br>-Nano-2512</th>
+      <th style="text-align: center;">Whisper<br>-large-v3</th>
+      <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="6" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Open-sourced Benchmarks</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MLS</td>
+      <td style="text-align: center;">13.32</td>
+      <td style="text-align: center;">8.62</td>
+      <td style="text-align: center;">28.70</td>
+      <td style="text-align: center;">13.19</td>
+      <td style="text-align: center;"><strong>8.55</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">CommonVoice</td>
+      <td style="text-align: center;">19.40</td>
+      <td style="text-align: center;">10.77</td>
+      <td style="text-align: center;">17.25</td>
+      <td style="text-align: center;">12.75</td>
+      <td style="text-align: center;"><strong>9.18</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MLC-SLM</td>
+      <td style="text-align: center;">34.93</td>
+      <td style="text-align: center;">15.68</td>
+      <td style="text-align: center;">29.94</td>
+      <td style="text-align: center;">15.84</td>
+      <td style="text-align: center;"><strong>12.74</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Fleurs</td>
+      <td style="text-align: center;">16.08</td>
+      <td style="text-align: center;">5.27</td>
+      <td style="text-align: center;">10.03</td>
+      <td style="text-align: center;">7.57</td>
+      <td style="text-align: center;"><strong>4.90</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Fleurs<sup>†</sup></td>
+      <td style="text-align: center;">20.05</td>
+      <td style="text-align: center;">6.85</td>
+      <td style="text-align: center;">31.89</td>
+      <td style="text-align: center;">10.37</td>
+      <td style="text-align: center;"><strong>6.62</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Fleurs<sup>††</sup></td>
+      <td style="text-align: center;">24.83</td>
+      <td style="text-align: center;"><strong>8.16</strong></td>
+      <td style="text-align: center;">47.84</td>
+      <td style="text-align: center;">21.80</td>
+      <td style="text-align: center;">12.60</td>
+    </tr>
+    <tr>
+      <td colspan="6" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Qwen-ASR Internal Benchmarks</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">News-Multilingual</td>
+      <td style="text-align: center;">49.40</td>
+      <td style="text-align: center;">14.80</td>
+      <td style="text-align: center;">65.07</td>
+      <td style="text-align: center;">17.39</td>
+      <td style="text-align: center;"><strong>12.80</strong></td>
+    </tr>
+  </tbody>
+</table>
+<p><strong>Language coverage:</strong> <em>MLS</em> includes 8 languages: {da, de, en, es, fr, it, pl, pt}.<br><em>CommonVoice</em> includes 13 languages: {en, zh, yue, zh_TW, ar, de, es, fr, it, ja, ko, pt, ru}.<br><em>MLC-SLM</em> includes 11 languages: {en, fr, de, it, pt, es, ja, ko, ru, th, vi}.<br><em>Fleurs</em> includes 12 languages: {en, zh, yue, ar, de, es, fr, it, ja, ko, pt, ru }.<br><em>Fleurs<sup>†</sup></em> includes 8 additional languages beyond Fleurs: {hi, id, ms, nl, pl, th, tr, vi}.<br><em>Fleurs<sup>††</sup></em> includes 10 additional languages beyond Fleurs<sup>†</sup>: {cs, da, el, fa, fi, fil, hu, mk, ro, sv}.<br><em>News-Multilingual</em> includes 15 languages: {ar, de, es, fr, hi, id, it, ja, ko, nl, pl, pt, ru, th, vi}.</p>
+
+</details>
+
+<details>
+<summary>Language Identification Accuracy (%) ↑</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;"></th>
+      <th style="text-align: center;">Whisper-large-v3</th>
+      <th style="text-align: center;">Qwen3-ASR-0.6B</th>
+      <th style="text-align: center;">Qwen3-ASR-1.7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td style="text-align: left;">MLS</td>
+      <td style="text-align: center;"><strong>99.9</strong></td>
+      <td style="text-align: center;">99.3</td>
+      <td style="text-align: center;"><strong>99.9</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">CommonVoice</td>
+      <td style="text-align: center;">92.7</td>
+      <td style="text-align: center;"><strong>98.2<strong></td>
+      <td style="text-align: center;"><strong>98.7</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MLC-SLM</td>
+      <td style="text-align: center;">89.2</td>
+      <td style="text-align: center;"><strong>92.7<strong></td>
+      <td style="text-align: center;"><strong>94.1</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Fleurs</td>
+      <td style="text-align: center;">94.6</td>
+      <td style="text-align: center;"><strong>97.1<strong></td>
+      <td style="text-align: center;"><strong>98.7</strong></td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td style="text-align: left;"><em>Avg.</em></td>
+      <td style="text-align: center;">94.1</td>
+      <td style="text-align: center;"><strong>96.8<strong></td>
+      <td style="text-align: center;"><strong>97.9</strong></td>
+    </tr>
+  </tbody>
+</table>
+<p><strong>Language coverage:</strong> The language sets follow Multilingual ASR Benchmarks. Here, Fleurs corresponds to Fleurs<sup>††</sup> in Multilingual ASR Benchmarks and covers 30 languages.</p>
+
+</details>
+
+<details>
+<summary>Singing Voice & Song Transcription (WER ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;"></th>
+      <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
+      <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
+      <th style="text-align: center;">Doubao-ASR<br>-1.0</th>
+      <th style="text-align: center;">Whisper<br>-large-v3</th>
+      <th style="text-align: center;">Fun-ASR-MLT<br>-Nano</th>
+      <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="7" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Singing</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">M4Singer</td>
+      <td style="text-align: center;">16.77</td>
+      <td style="text-align: center;">20.88</td>
+      <td style="text-align: center;">7.88</td>
+      <td style="text-align: center;">13.58</td>
+      <td style="text-align: center;">7.29</td>
+      <td style="text-align: center;"><strong>5.98</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">MIR-1k-vocal</td>
+      <td style="text-align: center;">11.87</td>
+      <td style="text-align: center;">9.85</td>
+      <td style="text-align: center;">6.56</td>
+      <td style="text-align: center;">11.71</td>
+      <td style="text-align: center;">8.17</td>
+      <td style="text-align: center;"><strong>6.25</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Opencpop</td>
+      <td style="text-align: center;">7.93</td>
+      <td style="text-align: center;">6.49</td>
+      <td style="text-align: center;">3.80</td>
+      <td style="text-align: center;">9.52</td>
+      <td style="text-align: center;"><strong>2.98</strong></td>
+      <td style="text-align: center;">3.08</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Popcs</td>
+      <td style="text-align: center;">32.84</td>
+      <td style="text-align: center;">15.13</td>
+      <td style="text-align: center;">8.97</td>
+      <td style="text-align: center;">13.77</td>
+      <td style="text-align: center;">9.42</td>
+      <td style="text-align: center;"><strong>8.52</strong></td>
+    </tr>
+    <tr>
+      <td colspan="7" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Songs with BGM</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">EntireSongs-en</td>
+      <td style="text-align: center;">30.71</td>
+      <td style="text-align: center;"><strong>12.18</strong></td>
+      <td style="text-align: center;">33.51</td>
+      <td style="text-align: center;">N/A</td>
+      <td style="text-align: center;">N/A</td>
+      <td style="text-align: center;">14.60</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">EntireSongs-zh</td>
+      <td style="text-align: center;">34.86</td>
+      <td style="text-align: center;">18.68</td>
+      <td style="text-align: center;">23.99</td>
+      <td style="text-align: center;">N/A</td>
+      <td style="text-align: center;">N/A</td>
+      <td style="text-align: center;"><strong>13.91</strong></td>
+    </tr>
+  </tbody>
+</table>
+
+</details>
+
+<details>
+<summary>ASR Inference Mode Performance (WER ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;">Model</th>
+      <th style="text-align: left;">Infer. Mode</th>
+      <th style="text-align: center;">Librispeech</th>
+      <th style="text-align: center;">Fleurs-en</th>
+      <th style="text-align: center;">Fleurs-zh</th>
+      <th style="text-align: center;">Avg.</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="2" style="text-align: left; vertical-align: middle;">Qwen3-ASR-1.7B</td>
+      <td style="text-align: left;">Offline</td>
+      <td style="text-align: center;">1.63 | 3.38</td>
+      <td style="text-align: center;">3.35</td>
+      <td style="text-align: center;">2.41</td>
+      <td style="text-align: center;">2.69</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Streaming</td>
+      <td style="text-align: center;">1.95 | 4.51</td>
+      <td style="text-align: center;">4.02</td>
+      <td style="text-align: center;">2.84</td>
+      <td style="text-align: center;">3.33</td>
+    </tr>
+    <tr style="border-top: 1px solid #ddd;">
+      <td rowspan="2" style="text-align: left; vertical-align: middle;">Qwen3-ASR-0.6B</td>
+      <td style="text-align: left;">Offline</td>
+      <td style="text-align: center;">2.11 | 4.55</td>
+      <td style="text-align: center;">4.39</td>
+      <td style="text-align: center;">2.88</td>
+      <td style="text-align: center;">3.48</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Streaming</td>
+      <td style="text-align: center;">2.54 | 6.27</td>
+      <td style="text-align: center;">5.38</td>
+      <td style="text-align: center;">3.40</td>
+      <td style="text-align: center;">4.40</td>
+    </tr>
+  </tbody>
+</table>
+
+</details>
+
+<details>
+<summary>Forced Alignment Benchmarks (AAS ms ↓)</summary>
+
+<table>
+  <thead>
+    <tr>
+      <th style="text-align: left;"></th>
+      <th style="text-align: center;">Monotonic-Aligner</th>
+      <th style="text-align: center;">NFA</th>
+      <th style="text-align: center;">WhisperX</th>
+      <th style="text-align: center;">Qwen3-ForcedAligner-0.6B</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">MFA-Labeled Raw</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Chinese</td>
+      <td style="text-align: center;">161.1</td>
+      <td style="text-align: center;">109.8</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>33.1</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">English</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">107.5</td>
+      <td style="text-align: center;">92.1</td>
+      <td style="text-align: center;"><strong>37.5</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">French</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">100.7</td>
+      <td style="text-align: center;">145.3</td>
+      <td style="text-align: center;"><strong>41.7</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">German</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">122.7</td>
+      <td style="text-align: center;">165.1</td>
+      <td style="text-align: center;"><strong>46.5</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Italian</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">142.7</td>
+      <td style="text-align: center;">155.5</td>
+      <td style="text-align: center;"><strong>75.5</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Japanese</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>42.2</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Korean</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>37.2</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Portuguese</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>38.4</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Russian</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">200.7</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>40.2</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spanish</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">124.7</td>
+      <td style="text-align: center;">108.0</td>
+      <td style="text-align: center;"><strong>36.8</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;"><em>Avg.</em></td>
+      <td style="text-align: center;">161.1</td>
+      <td style="text-align: center;">129.8</td>
+      <td style="text-align: center;">133.2</td>
+      <td style="text-align: center;"><strong>42.9</strong></td>
+    </tr>
+    <tr>
+      <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">MFA-Labeled Concat-300s</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Chinese</td>
+      <td style="text-align: center;">1742.4</td>
+      <td style="text-align: center;">235.0</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>36.5</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">English</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">226.7</td>
+      <td style="text-align: center;">227.2</td>
+      <td style="text-align: center;"><strong>58.6</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">French</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">230.6</td>
+      <td style="text-align: center;">2052.2</td>
+      <td style="text-align: center;"><strong>53.4</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">German</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">220.3</td>
+      <td style="text-align: center;">993.4</td>
+      <td style="text-align: center;"><strong>62.4</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Italian</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">290.5</td>
+      <td style="text-align: center;">5719.4</td>
+      <td style="text-align: center;"><strong>81.6</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Japanese</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>81.3</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Korean</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>42.2</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Portuguese</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>50.0</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Russian</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">283.3</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>43.0</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Spanish</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;">240.2</td>
+      <td style="text-align: center;">4549.9</td>
+      <td style="text-align: center;"><strong>39.6</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Cross-lingual</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>34.2</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;"><em>Avg.</em></td>
+      <td style="text-align: center;">1742.4</td>
+      <td style="text-align: center;">246.7</td>
+      <td style="text-align: center;">2708.4</td>
+      <td style="text-align: center;"><strong>52.9</strong></td>
+    </tr>
+    <tr>
+      <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Human-Labeled</td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Raw</td>
+      <td style="text-align: center;">49.9</td>
+      <td style="text-align: center;">88.6</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>27.8</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Raw-Noisy</td>
+      <td style="text-align: center;">53.3</td>
+      <td style="text-align: center;">89.5</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>41.8</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Concat-60s</td>
+      <td style="text-align: center;">51.1</td>
+      <td style="text-align: center;">86.7</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>25.3</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Concat-300s</td>
+      <td style="text-align: center;">410.8</td>
+      <td style="text-align: center;">140.0</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>24.8</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;">Concat-Cross-lingual</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>42.5</strong></td>
+    </tr>
+    <tr>
+      <td style="text-align: left;"><em>Avg.</em></td>
+      <td style="text-align: center;">141.3</td>
+      <td style="text-align: center;">101.2</td>
+      <td style="text-align: center;">-</td>
+      <td style="text-align: center;"><strong>32.4</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-ASR,
+  title={Qwen3-ASR Technical Report},
+  author={Xian Shi, Xiong Wang, Zhifang Guo, Yongqi Wang, Pei Zhang, Xinyu Zhang, Zishan Guo, Hongkun Hao, Yu Xi, Baosong Yang, Jin Xu, Jingren Zhou, Junyang Lin},
+  journal={arXiv preprint arXiv:2601.21337},
+  year={2026}
+}
+```
+
+
+<br>

Qwen3-ForcedAligner-0.6B/chat_template.json

@@ -0,0 +1 @@
+{"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n  {%- if m.role == 'system' -%}\n    {%- if m.content is string -%}\n      {%- set ns.system_text = ns.system_text + m.content -%}\n    {%- else -%}\n      {%- for c in m.content -%}\n        {%- if c.type == 'text' and (c.text is defined) -%}\n          {%- set ns.system_text = ns.system_text + c.text -%}\n        {%- endif -%}\n      {%- endfor -%}\n    {%- endif -%}\n  {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n  {%- if m.content is not string -%}\n    {%- for c in m.content -%}\n      {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n        {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n      {%- endif -%}\n    {%- endfor -%}\n  {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"}

Qwen3-ForcedAligner-0.6B/config.json

@@ -0,0 +1,205 @@
+{
+    "architectures": [
+      "Qwen3ASRForConditionalGeneration"
+    ],
+    "timestamp_token_id": 151705,
+    "timestamp_segment_time": 80,
+    "model_type": "qwen3_asr",
+    "support_languages": [
+      "Chinese",
+      "Cantonese",
+      "English",
+      "German",
+      "Spanish",
+      "French",
+      "Italian",
+      "Portuguese",
+      "Russian",
+      "Korean",
+      "Japanese"
+    ],
+    "thinker_config": {
+      "model_type": "qwen3_forced_aligner",
+      "classify_num": 5000,
+      "architectures": [
+        "Qwen3ASRForConditionalGeneration"
+      ],
+      "audio_config": {
+        "_name_or_path": "",
+        "activation_dropout": 0,
+        "activation_function": "gelu",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_dropout": 0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "conv_chunksize": 500,
+        "cross_attention_hidden_size": null,
+        "d_model": 1024,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "downsample_hidden_size": 480,
+        "dropout": 0,
+        "dtype": null,
+        "early_stopping": false,
+        "encoder_attention_heads": 16,
+        "encoder_ffn_dim": 4096,
+        "encoder_layers": 24,
+        "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,
+        "id2label": {
+          "0": "LABEL_0",
+          "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+          "LABEL_0": 0,
+          "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "max_source_positions": 1500,
+        "min_length": 0,
+        "model_type": "qwen3_asr_audio_encoder",
+        "n_window": 50,
+        "n_window_infer": 800,
+        "no_repeat_ngram_size": 0,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 24,
+        "num_mel_bins": 128,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_dim": 1024,
+        "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,
+        "scale_embedding": false,
+        "sep_token_id": 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,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false
+      },
+      "audio_end_token_id": 151670,
+      "audio_start_token_id": 151669,
+      "audio_token_id": 151676,
+      "dtype": "bfloat16",
+      "initializer_range": 0.02,
+      "text_config": {
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "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,
+        "dtype": null,
+        "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
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "max_position_embeddings": 8192,
+        "min_length": 0,
+        "model_type": "qwen3",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 16,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 28,
+        "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": {
+          "interleaved": true,
+          "mrope_interleaved": true,
+          "mrope_section": [
+            24,
+            20,
+            20
+          ],
+          "rope_type": "default",
+          "type": "default"
+        },
+        "rope_theta": 1000000,
+        "sep_token_id": 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,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "use_cache": true,
+        "vocab_size": 152064
+      }
+    },
+    "transformers_version": "4.57.6"
+  }
+  

Qwen3-ForcedAligner-0.6B/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [151643,151645],
+  "pad_token_id": 151643,
+  "do_sample": false
+}

Qwen3-ForcedAligner-0.6B/issues.txt

@@ -0,0 +1,46 @@
+----------------------------------------------------------------------
+#3 chatllm.cpp gets support of this model
+----------------------------------------------------------------------
+
+[J22] Feb 1, 2026
+
+chatllm.cpp supports Qwen3-ASR & Qwen3-ForcedAligner models.
+
+main.exe -m .../qwen3-focedaligner-0.6b.bin --multimedia_file_tags {{ }} -i --set delimiter "|"
+    ________          __  __    __    __  ___ 
+   / ____/ /_  ____ _/ /_/ /   / /   /  |/  /_________  ____
+  / /   / __ \/ __ `/ __/ /   / /   / /|_/ // ___/ __ \/ __ \
+ / /___/ / / / /_/ / /_/ /___/ /___/ /  / // /__/ /_/ / /_/ /
+ \____/_/ /_/\__,_/\__/_____/_____/_/  /_(_)___/ .___/ .___/
+You are served by Qwen3-ForcedAligner,        /_/   /_/
+with 601300992 (0.6B) parameters.
+
+You  > {{audio:...\Downloads\asr_zh.wav}}甚至|出现交易|几乎停滞|的情况。
+A.I. > 0
+00:00:00,400 --> 00:00:00,960
+甚至
+
+1
+00:00:00,960 --> 00:00:02,000
+出现交易
+
+2
+00:00:02,000 --> 00:00:02,879
+几乎停滞
+
+3
+00:00:02,879 --> 00:00:03,680
+的情况。
+
+[lbarasc] Feb 10, 2026
+
+i want to use this on windows, i downloaded the latest chatllm and a mp3 speech of Obama for example, but i don't have any text in output !
+please submit links to download chatllm, qwen3-focedaligner-0.6b.bin and the .wav.
+can i forgot something ?
+thank you
+
+[J22] Feb 11, 2026
+
+@lbarasc, you can find quantized models here: https://modelscope.cn/models/judd2024/chatllm_quantized_qwen3/files
+
+Or, you can quantize them on your own by using convert.py.

Qwen3-ForcedAligner-0.6B/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

Qwen3-ForcedAligner-0.6B/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47831d0e82f96b20e9034dba01a075ee06436654719f6a68289e49f1b65ce0e7
+size 1835544544

Qwen3-ForcedAligner-0.6B/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Qwen3ASRProcessor",
+  "return_attention_mask": true
+}

Qwen3-ForcedAligner-0.6B/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B

Qwen3-ForcedAligner-0.6B/tokenizer_config.json

@@ -0,0 +1,557 @@
+{
+  "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": "<non_speech>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151676": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<blank1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<blank2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<blank3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<blank4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<blank5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<blank6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<blank7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<blank8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<blank9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<blank10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<blank11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<blank12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<blank13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<blank14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<blank15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<blank16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<blank17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<blank18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<blank19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<blank20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151697": {
+      "content": "<blank21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151698": {
+      "content": "<blank22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151699": {
+      "content": "<blank23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151700": {
+      "content": "<blank24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151701": {
+      "content": "<blank25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151702": {
+      "content": "<blank26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151703": {
+      "content": "<blank27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151704": {
+      "content": "<asr_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151705": {
+      "content": "<timestamp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "image_token": "<|image_pad|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3ASRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

chatllm_quantized_qwen3/.gitattributes

@@ -0,0 +1,93 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-4b-it.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-2b-it.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-a3b-it.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-a3b-it-q4_1.bin filter=lfs diff=lfs merge=lfs -text
+
+mai-ui-2b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-a3b-thinking-q4_1.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-a3b-thinking.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-emb-2b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-reranker-2b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-vl-8b-it.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-asr-0.6b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-asr-1.7b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-focedaligner-0.6b.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-focedaligner-0.6b-f16.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-0.6b-base.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-0.6b-customvoice.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-1.7b-base.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-1.7b-customvoice.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-1.7b-voicedesign.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-0.6b-base-f16.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-0.6b-customvoice-f16.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-1.7b-base-f16.bin filter=lfs diff=lfs merge=lfs -text
+
+qwen3-tts-12hz-1.7b-customvoice-f16.bin filter=lfs diff=lfs merge=lfs -text

chatllm_quantized_qwen3/README.md

@@ -0,0 +1,13 @@
+---
+frameworks:
+- other
+license: other
+tasks:
+- text-generation
+---
+
+这里包含一系列预先量化的 LLM，可供 [ChatLLM.cpp](https://github.com/foldl/chatllm.cpp) 直接使用。
+
+**注意**：这里出于研究、学习之目的提供量化模型，每种模型的使用请遵循相应的用户协议。
+
+

chatllm_quantized_qwen3/mai-ui-2b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c2b94e99f3abc43613f91dc0ffbc80aab880abe4e2e5b8ce45f103ea3ef81b
+size 2267737776

chatllm_quantized_qwen3/qwen3-asr-0.6b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56af60844e85e812641c4c9370af669fdfe4888ca41f93272d9db769efca9afe
+size 1005656864

chatllm_quantized_qwen3/qwen3-asr-1.7b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6400749342f9ed5ce2f5fabdd0332441ff118a81d6b9d195d462b668d0d017a
+size 2505570400

chatllm_quantized_qwen3/qwen3-focedaligner-0.6b-f16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272a24687e3f92cf60daa5a332991176e08feef1bd79b0626e626d49fe23f604
+size 1840552064

chatllm_quantized_qwen3/qwen3-focedaligner-0.6b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfccb1316a7bc890660fc5d1c8bbcc6477b05fb0ca13417aa65a1443f85089d5
+size 984439424

chatllm_quantized_qwen3/source.txt

@@ -0,0 +1 @@
+https://modelscope.cn/models/judd2024/chatllm_quantized_qwen3

qwen3-asr-0.6b-f16/.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
+qwen3-asr-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text

qwen3-asr-0.6b-f16/README.md

@@ -0,0 +1,80 @@
+
+---
+language: 
+- zh
+- en
+- yue
+- ar
+- de
+- fr
+- es
+- pt
+- id
+- it
+- ko
+- ru
+- th
+- vi
+- ja
+- tr
+- hi
+- ms
+- nl
+- sv
+- da
+- fi
+- pl
+- cs
+- fil
+- fa
+- el
+- hu
+- mk
+- ro
+tags:
+- audio
+- speech
+- automatic-speech-recognition
+---
+
+license: apache-2.0
+---
+
+# OVOS - Qwen3 ASR 0.6B F16 (GGUF)
+
+This model is a quantized gguf-format export of [Qwen/Qwen3-ASR-0.6B](https://huggingface.co/Qwen/Qwen3-ASR-0.6B)
+for ease of use in edge devices and CPU-based inference environments.
+The original model is transformed into gguf with F16 tensors by the script [convert_hf_to_gguf.py](https://github.com/femelo/qwen3-asr.cpp/blob/main/scripts/convert_hf_to_gguf.py)
+and then further quantized, if needed, using the tool [quantize](https://github.com/femelo/qwen3-asr.cpp/blob/main/src/quantize.cpp) from the same repo.
+
+# Requirements
+
+The requirements can be installed as
+
+```bash
+$ pip install git+https://github.com/femelo/py-qwen3-asr-cpp
+```
+
+# Usage
+
+```python
+from py_qwen3_asr_cpp.model import Qwen3ASRModel
+
+# Initialize the model (it handles downloading from this repo)
+model = Qwen3ASRModel(
+    asr_model="qwen3-asr-0.6b-f16",
+    n_threads=4
+)
+
+# Transcribe from file
+result = model.transcribe("audio.mp3")
+print(f"Detected Language: {result.language}")
+print(f"Transcription: {result.text}")
+```
+
+Refer to [https://github.com/femelo/py-qwen3-asr-cpp](https://github.com/femelo/py-qwen3-asr-cpp) for more details.
+
+# Licensing
+
+The license is derived from the original model: Apache 2.0. For more details, please refer to [Qwen/Qwen3-ASR-0.6B](https://huggingface.co/Qwen/Qwen3-ASR-0.6B).
+

qwen3-asr-0.6b-f16/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

qwen3-asr-0.6b-f16/qwen3-asr-0.6b-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fbc2a779f45002e912fb716b031287659bf6d9036dd78447a3cabc06fe2f43
+size 1882543424

qwen3-asr-0.6b-f16/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/OpenVoiceOS/qwen3-asr-0.6b-f16

qwen3-forced-aligner-0.6b-f16/.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
+qwen3-forced-aligner-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text

qwen3-forced-aligner-0.6b-f16/README.md

@@ -0,0 +1,81 @@
+
+---
+language: 
+- zh
+- en
+- yue
+- ar
+- de
+- fr
+- es
+- pt
+- id
+- it
+- ko
+- ru
+- th
+- vi
+- ja
+- tr
+- hi
+- ms
+- nl
+- sv
+- da
+- fi
+- pl
+- cs
+- fil
+- fa
+- el
+- hu
+- mk
+- ro
+tags:
+- audio
+- speech
+- automatic-speech-recognition
+---
+
+license: apache-2.0
+---
+
+# OVOS - Qwen3 Forced Aligner 0.6B F16 (GGUF)
+
+This model is a quantized gguf-format export of [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B)
+for ease of use in edge devices and CPU-based inference environments.
+The original model is transformed into gguf with F16 tensors by the script [convert_hf_to_gguf.py](https://github.com/femelo/qwen3-asr.cpp/blob/main/scripts/convert_hf_to_gguf.py)
+and then further quantized, if needed, using the tool [quantize](https://github.com/femelo/qwen3-asr.cpp/blob/main/src/quantize.cpp) from the same repo.
+
+# Requirements
+
+The requirements can be installed as
+
+```bash
+$ pip install git+https://github.com/femelo/py-qwen3-asr-cpp
+```
+
+# Usage
+
+```python
+from py_qwen3_asr_cpp.model import Qwen3ASRModel
+
+# Initialize the model (it handles downloading from this repo)
+model = Qwen3ASRModel(
+    asr_model="qwen3-asr-0.6b-f16",
+    align_model="qwen3-forced-aligner-0.6b-f16",
+    n_threads=4
+)
+
+# Transcribe from file
+result, alignment = model.transcribe_and_align("audio.mp3")
+print(f"Detected Language: {result.language}")
+print(f"Transcription: {result.text}")
+```
+
+Refer to [https://github.com/femelo/py-qwen3-asr-cpp](https://github.com/femelo/py-qwen3-asr-cpp) for more details.
+
+# Licensing
+
+The license is derived from the original model: Apache 2.0. For more details, please refer to [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B).
+

qwen3-forced-aligner-0.6b-f16/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

qwen3-forced-aligner-0.6b-f16/qwen3-forced-aligner-0.6b-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70b52245d6554260bba88c17a6ff090ac60476506e4374eb4ce015ab156abab
+size 1842214208

qwen3-forced-aligner-0.6b-f16/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/OpenVoiceOS/qwen3-forced-aligner-0.6b-f16

qwen3-forced-aligner-0.6b-q4-k-m/.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
+qwen3-forced-aligner-0.6b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text

qwen3-forced-aligner-0.6b-q4-k-m/README.md

@@ -0,0 +1,81 @@
+
+---
+language: 
+- zh
+- en
+- yue
+- ar
+- de
+- fr
+- es
+- pt
+- id
+- it
+- ko
+- ru
+- th
+- vi
+- ja
+- tr
+- hi
+- ms
+- nl
+- sv
+- da
+- fi
+- pl
+- cs
+- fil
+- fa
+- el
+- hu
+- mk
+- ro
+tags:
+- audio
+- speech
+- automatic-speech-recognition
+---
+
+license: apache-2.0
+---
+
+# OVOS - Qwen3 Forced Aligner 0.6B Q4_K_M (GGUF)
+
+This model is a quantized gguf-format export of [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B)
+for ease of use in edge devices and CPU-based inference environments.
+The original model is transformed into gguf with F16 tensors by the script [convert_hf_to_gguf.py](https://github.com/femelo/qwen3-asr.cpp/blob/main/scripts/convert_hf_to_gguf.py)
+and then further quantized, if needed, using the tool [quantize](https://github.com/femelo/qwen3-asr.cpp/blob/main/src/quantize.cpp) from the same repo.
+
+# Requirements
+
+The requirements can be installed as
+
+```bash
+$ pip install git+https://github.com/femelo/py-qwen3-asr-cpp
+```
+
+# Usage
+
+```python
+from py_qwen3_asr_cpp.model import Qwen3ASRModel
+
+# Initialize the model (it handles downloading from this repo)
+model = Qwen3ASRModel(
+    asr_model="qwen3-asr-0.6b-q4-k-m",
+    align_model="qwen3-forced-aligner-0.6b-q4-k-m",
+    n_threads=4
+)
+
+# Transcribe from file
+result, alignment = model.transcribe_and_align("audio.mp3")
+print(f"Detected Language: {result.language}")
+print(f"Transcription: {result.text}")
+```
+
+Refer to [https://github.com/femelo/py-qwen3-asr-cpp](https://github.com/femelo/py-qwen3-asr-cpp) for more details.
+
+# Licensing
+
+The license is derived from the original model: Apache 2.0. For more details, please refer to [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B).
+

qwen3-forced-aligner-0.6b-q4-k-m/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

qwen3-forced-aligner-0.6b-q4-k-m/qwen3-forced-aligner-0.6b-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542687c8ddb39f9f6510dd7db99697f70ed1148cd3cd7ddbae22097cce73dd6e
+size 615667968

qwen3-forced-aligner-0.6b-q4-k-m/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/OpenVoiceOS/qwen3-forced-aligner-0.6b-q4-k-m

qwen3-forced-aligner-0.6b-q5-k-m/.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
+qwen3-forced-aligner-0.6b-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text

qwen3-forced-aligner-0.6b-q5-k-m/README.md

@@ -0,0 +1,81 @@
+
+---
+language: 
+- zh
+- en
+- yue
+- ar
+- de
+- fr
+- es
+- pt
+- id
+- it
+- ko
+- ru
+- th
+- vi
+- ja
+- tr
+- hi
+- ms
+- nl
+- sv
+- da
+- fi
+- pl
+- cs
+- fil
+- fa
+- el
+- hu
+- mk
+- ro
+tags:
+- audio
+- speech
+- automatic-speech-recognition
+---
+
+license: apache-2.0
+---
+
+# OVOS - Qwen3 Forced Aligner 0.6B Q5_K_M (GGUF)
+
+This model is a quantized gguf-format export of [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B)
+for ease of use in edge devices and CPU-based inference environments.
+The original model is transformed into gguf with F16 tensors by the script [convert_hf_to_gguf.py](https://github.com/femelo/qwen3-asr.cpp/blob/main/scripts/convert_hf_to_gguf.py)
+and then further quantized, if needed, using the tool [quantize](https://github.com/femelo/qwen3-asr.cpp/blob/main/src/quantize.cpp) from the same repo.
+
+# Requirements
+
+The requirements can be installed as
+
+```bash
+$ pip install git+https://github.com/femelo/py-qwen3-asr-cpp
+```
+
+# Usage
+
+```python
+from py_qwen3_asr_cpp.model import Qwen3ASRModel
+
+# Initialize the model (it handles downloading from this repo)
+model = Qwen3ASRModel(
+    asr_model="qwen3-asr-0.6b-q5-k-m",
+    align_model="qwen3-forced-aligner-0.6b-q5-k-m",
+    n_threads=4
+)
+
+# Transcribe from file
+result, alignment = model.transcribe_and_align("audio.mp3")
+print(f"Detected Language: {result.language}")
+print(f"Transcription: {result.text}")
+```
+
+Refer to [https://github.com/femelo/py-qwen3-asr-cpp](https://github.com/femelo/py-qwen3-asr-cpp) for more details.
+
+# Licensing
+
+The license is derived from the original model: Apache 2.0. For more details, please refer to [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B).
+

qwen3-forced-aligner-0.6b-q5-k-m/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

qwen3-forced-aligner-0.6b-q5-k-m/qwen3-forced-aligner-0.6b-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40ef91407268fa1a07ffb3df32d4f3bc2eb01c694fa533ba06b27279f0dbbed
+size 710352128

qwen3-forced-aligner-0.6b-q5-k-m/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/OpenVoiceOS/qwen3-forced-aligner-0.6b-q5-k-m

qwen3-forced-aligner-0.6b-q8-0/.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
+qwen3-forced-aligner-0.6b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

qwen3-forced-aligner-0.6b-q8-0/README.md

@@ -0,0 +1,81 @@
+
+---
+language: 
+- zh
+- en
+- yue
+- ar
+- de
+- fr
+- es
+- pt
+- id
+- it
+- ko
+- ru
+- th
+- vi
+- ja
+- tr
+- hi
+- ms
+- nl
+- sv
+- da
+- fi
+- pl
+- cs
+- fil
+- fa
+- el
+- hu
+- mk
+- ro
+tags:
+- audio
+- speech
+- automatic-speech-recognition
+---
+
+license: apache-2.0
+---
+
+# OVOS - Qwen3 Forced Aligner 0.6B Q8_0 (GGUF)
+
+This model is a quantized gguf-format export of [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B)
+for ease of use in edge devices and CPU-based inference environments.
+The original model is transformed into gguf with F16 tensors by the script [convert_hf_to_gguf.py](https://github.com/femelo/qwen3-asr.cpp/blob/main/scripts/convert_hf_to_gguf.py)
+and then further quantized, if needed, using the tool [quantize](https://github.com/femelo/qwen3-asr.cpp/blob/main/src/quantize.cpp) from the same repo.
+
+# Requirements
+
+The requirements can be installed as
+
+```bash
+$ pip install git+https://github.com/femelo/py-qwen3-asr-cpp
+```
+
+# Usage
+
+```python
+from py_qwen3_asr_cpp.model import Qwen3ASRModel
+
+# Initialize the model (it handles downloading from this repo)
+model = Qwen3ASRModel(
+    asr_model="qwen3-asr-0.6b-q8-0",
+    align_model="qwen3-forced-aligner-0.6b-q8-0",
+    n_threads=4
+)
+
+# Transcribe from file
+result, alignment = model.transcribe_and_align("audio.mp3")
+print(f"Detected Language: {result.language}")
+print(f"Transcription: {result.text}")
+```
+
+Refer to [https://github.com/femelo/py-qwen3-asr-cpp](https://github.com/femelo/py-qwen3-asr-cpp) for more details.
+
+# Licensing
+
+The license is derived from the original model: Apache 2.0. For more details, please refer to [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B).
+

qwen3-forced-aligner-0.6b-q8-0/languages.txt

@@ -0,0 +1,30 @@
+Chinese + 22 Chinese dialects
+English
+Yue Chinese
+Arabic
+German
+French
+Spanish
+Portuguese
+Indonesian
+Italian
+Korean
+Russian
+Thai
+Vietnamese
+Japanese
+Turkish
+Hindi
+Malay
+Dutch
+Swedish
+Danish
+Finnish
+Polish
+Czech
+Filipino
+Persian
+Greek
+Hungarian
+Macedonian
+Romanian

qwen3-forced-aligner-0.6b-q8-0/qwen3-forced-aligner-0.6b-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de69a8cfc49c95a6520f50f2f15cfce9af35bc4723a10c56fc64e51dc966b3a
+size 994404608

qwen3-forced-aligner-0.6b-q8-0/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/OpenVoiceOS/qwen3-forced-aligner-0.6b-q8-0