--- title: X-ASR-zh-en canonical_url: "https://www.modelscope.ai/models/Gilgamesh-J/X-ASR-zh-en" md_url: "https://www.modelscope.ai/models/Gilgamesh-J/X-ASR-zh-en.md" repository: Gilgamesh-J/X-ASR-zh-en last_updated: 2026-07-29 license: apache-2.0 model_type: - x-asr-zipformer-transducer architectures: - Zipformer base_model_relation: finetune library_name: - onnx language: - zh - en downloads: 2961 stars: 0 tags: - automatic-speech-recognition - streaming-asr - offline-asr - icefall - k2 - zipformer - transducer - sherpa-onnx - onnx - chinese - english --- # X-ASR-zh-en > X-ASR-zh-en - An open-source model by Gilgamesh-J on ModelScope. Chinese-English offline-streaming unified ASR model artifacts for low-latency deployment. Gilgamesh-J/X-ASR-zh-en is a machine learning model on ModelScope. licensed under apache-2.0. - **Repository**: Gilgamesh-J/X-ASR-zh-en - **License**: apache-2.0 - **Tags**: automatic-speech-recognition, streaming-asr, offline-asr, icefall, k2, zipformer, transducer, sherpa-onnx, onnx, chinese, english - **Downloads**: 2961 - **Stars**: 0 - **Last updated**: 2026-07-29 Source: https://www.modelscope.ai/models/Gilgamesh-J/X-ASR-zh-en ---

🎙️ X-ASR-zh-en

Chinese-English offline-streaming unified ASR model artifacts for low-latency deployment.

Shanghai Jiao Tong University Shanghai Innovation Institute Fudan University Huazhong University of Science and Technology

Participating Institutions

🌐 GitHub Project | 🤗 Hugging Face Hub | 🧩 ModelScope | 🪐 Hugging Face Space | 🎧 Online Demo | 🚀 Deployment Guide

📄 X-ASR-zh-en Technical Report: Coming Soon

Model released Languages Streaming Deployment License

🔍 Model Card Scope | 📦 Repository Contents | 📊 Evaluation | ⬇️ Download | 🚀 Deployment

--- ## 🔍 Model Card Scope ### 🧩 X-ASR Series **X-ASR** is a series of automatic speech recognition models built with the **icefall** framework. The series focuses on **streaming ASR** and **low-latency deployment**, while also supporting offline recognition. The broader project roadmap, source organization, issue tracking, and bilingual documentation are maintained on the [GitHub project page](https://github.com/Gilgamesh-J/X-ASR). ### 🤖 X-ASR-zh-en **X-ASR-zh-en** is trained on approximately **1 million hours** of open-source and collected speech data. It is designed as an **offline-streaming unified transducer ASR model** with the **Zipformer architecture**, supporting both **offline decoding** and **true streaming decoding**. The model provides multiple streaming chunk sizes: **160 ms**, **480 ms**, **960 ms**, and **1920 ms**, supports **punctuation and casing**, and can be deployed with **sherpa-onnx**.

Zipformer architecture

## ✨ Artifact Page Notes This repository is the **model artifact page** for `X-ASR-zh-en`. | What this artifact page provides | What the GitHub project provides | |:---:|:---:| | Downloadable model artifacts | Project-level overview | | ONNX encoder / decoder / joiner files | Bilingual README and release notes | | `sherpa-onnx` deployment entry point | Source layout and issue tracking | | Model-card metadata, tags, license, and metrics | Development history and contribution workflow | ## 📦 Repository Contents | Path | Purpose | |:---:|:---:| | `deployment/` | Deployment-ready `sherpa-onnx` runtime files and examples | | `deployment/models/` | Exported streaming ONNX model variants | | `deployment/infer_and_client/` | WebSocket server, inference wrapper, and test client | | `figure/` | Architecture figure and demo preview media | | `demo/` | Demo video asset | | `applications/vibe-xasr/` | Vibe XASR desktop application package, manifest, and download notes | | `streaming_exp/` | Averaged/pretrained checkpoint artifact for research reference | ### Directory Layout ```text . |-- README.md |-- config.json |-- demo/ | `-- demo.mov |-- applications/ | `-- vibe-xasr/ | |-- README.md | |-- download_manifest.json | `-- VibeXASR-1.1.2-macos-universal.dmg |-- deployment/ | |-- README.md | |-- infer_and_client/ | | |-- README.md | | |-- sherpa_streaming_client.py | | |-- sherpa_streaming_infer.py | | `-- sherpa_streaming_server.py | `-- models/ | |-- chunk-160ms-model/ | | |-- encoder-160ms.onnx | | |-- decoder-160ms.onnx | | |-- joiner-160ms.onnx | | `-- tokens.txt | |-- chunk-480ms-model/ | |-- chunk-960ms-model/ | `-- chunk-1920ms-model/ |-- figure/ | |-- zipformer.png | |-- demo-preview.png | `-- institutions/ `-- streaming_exp/ `-- pretrained.pt ``` ## 🧩 Model Variants Each streaming variant contains a matched `encoder`, `decoder`, `joiner`, and `tokens.txt`. Do not mix files across model folders. | Directory | Encoder | Decoder | Joiner | Intended chunk | |:---:|:---:|:---:|:---:|:---:| | `deployment/models/chunk-160ms-model` | `encoder-160ms.onnx` | `decoder-160ms.onnx` | `joiner-160ms.onnx` | 160 ms | | `deployment/models/chunk-480ms-model` | `encoder-480ms.onnx` | `decoder-480ms.onnx` | `joiner-480ms.onnx` | 480 ms | | `deployment/models/chunk-960ms-model` | `encoder-960ms.onnx` | `decoder-960ms.onnx` | `joiner-960ms.onnx` | 960 ms | | `deployment/models/chunk-1920ms-model` | `encoder-1920ms.onnx` | `decoder-1920ms.onnx` | `joiner-1920ms.onnx` | 1920 ms | ## ⭐ Highlights | Category | Description | |:---:|:---:| | **Framework** | icefall / k2 | | **Architecture** | Zipformer transducer | | **Runtime** | sherpa-onnx | | **Languages** | Chinese and English | | **Training scale** | Approximately 1 million hours of open-source and collected speech data | | **Recognition modes** | Offline decoding and true streaming decoding | | **Streaming chunks** | 160 ms, 480 ms, 960 ms, 1920 ms | | **Text output** | Supports punctuation and casing | ## 📊 Evaluation The following results are for the current **X-ASR-zh-en** release. Values are **WER/CER percentages**; lower is better. All results are reported with **greedy search**.
Mode Chunk size LibriSpeech GigaSpeech WenetSpeech
clean other net meeting
Streaming 160 ms 3.91 10.17 10.97 9.45 12.04
Streaming 480 ms 3.14 7.57 9.77 7.38 9.31
Streaming 960 ms 3.12 7.22 9.62 6.96 8.84
Streaming 1920 ms 2.84 6.47 9.46 6.42 8.03
Offline - 2.69 5.76 9.23 5.96 7.20
**Note:** Bold numbers indicate the best result among the listed modes for each benchmark column. ### Public Benchmark Model Comparison The following table compares representative ASR models on the same public benchmark columns. Ranks are computed by **AVG** across the five listed columns; lower is better. Parameter sizes are shown when provided by the source sheet.
Rank Model Params LibriSpeech GigaSpeech WenetSpeech AVG
clean other net meeting
1Qwen3-ASR1.7B1.653.458.565.295.464.882
2Qwen3-ASR0.6B2.184.548.945.976.885.702
3X-ASR-zh-en (offline)0.16B2.565.569.175.837.066.036
4SenseVoice-small234M3.167.2111.245.736.476.762
5VibeVoice-ASR9B2.185.659.4914.4517.199.792
### GigaSpeechBench Vertical Domain Evaluation The following results report **GigaSpeechBench vertical-domain** performance for the current **X-ASR-zh-en** release. Values are **WER/CER percentages**; lower is better. Domain abbreviations follow the GigaSpeechBench vertical-domain labels. #### CH
Mode Chunk size ARG AIT ART BIO ECM ENG ENT FIN HUM LAW MED MIL
Streaming160 ms9.886.764.397.324.133.588.453.2310.426.584.252.55
Streaming480 ms8.676.173.606.223.783.047.042.789.435.843.762.11
Streaming960 ms8.005.693.446.103.692.886.712.729.075.583.692.11
Streaming1920 ms7.245.583.275.823.482.746.552.578.594.973.531.94
Offline-6.564.542.775.042.992.326.021.947.644.202.901.68
#### EN
Mode Chunk size ARG AIT ART BIO ECM ENG ENT FIN HUM LAW MED MIL
Streaming160 ms5.298.578.557.314.335.0116.255.587.3613.396.036.20
Streaming480 ms4.628.407.736.124.194.6514.505.216.7911.515.596.02
Streaming960 ms4.588.357.456.004.134.4413.995.126.5810.865.526.04
Streaming1920 ms4.338.326.905.894.004.3713.614.986.3910.525.455.78
Offline-4.098.286.735.484.124.3012.304.946.1710.415.355.61
## 🎧 Demo A **sherpa-onnx based online demo** is available here: - [https://stream-asr.sjtuxlance.com/](https://stream-asr.sjtuxlance.com/) Demo video: X-ASR demo video preview [Open demo video](demo/demo.mov) ## ⬇️ Download ### GitHub Use GitHub when you want the full project repository, bilingual documentation, training references, deployment examples, and issue-tracking context. ```bash git lfs install git clone https://github.com/Gilgamesh-J/X-ASR.git cd X-ASR git lfs pull ``` ### Hugging Face Use Hugging Face when you want the model artifact page and standard HF Hub download tooling. ```bash hf download GilgameshWind/X-ASR-zh-en \ --local-dir ./X-ASR-zh-en ``` You can also clone the Hugging Face repository with Git LFS: ```bash git lfs install git clone https://huggingface.co/GilgameshWind/X-ASR-zh-en cd X-ASR-zh-en git lfs pull ``` ### ModelScope Use ModelScope when you prefer the ModelScope mirror or Git LFS clone from ModelScope. ```bash git lfs install git clone https://www.modelscope.ai/Gilgamesh-J/X-ASR-zh-en.git cd X-ASR-zh-en git lfs pull ``` ## 🚀 Deployment The recommended runtime is **sherpa-onnx**. The shortest path is to use the deployment package in this repository. ```bash cd deployment python -m venv .venv source .venv/bin/activate python -m pip install --upgrade pip python -m pip install -r requirements.txt ``` Start a CPU streaming server with the 160 ms model: ```bash python infer_and_client/sherpa_streaming_server.py \ --host 0.0.0.0 \ --port 8766 \ --tokens models/chunk-160ms-model/tokens.txt \ --encoder models/chunk-160ms-model/encoder-160ms.onnx \ --decoder models/chunk-160ms-model/decoder-160ms.onnx \ --joiner models/chunk-160ms-model/joiner-160ms.onnx \ --provider cpu \ --sample-rate 16000 \ --feature-dim 80 \ --num-threads 1 \ --decoding-method greedy_search \ --model-type zipformer2 \ --enable-endpoint-detection 0 \ --text-format none ``` Optional interactive tail-probe mode: ```bash python infer_and_client/sherpa_streaming_server.py \ --host 0.0.0.0 \ --port 8766 \ --tokens models/chunk-160ms-model/tokens.txt \ --encoder models/chunk-160ms-model/encoder-160ms.onnx \ --decoder models/chunk-160ms-model/decoder-160ms.onnx \ --joiner models/chunk-160ms-model/joiner-160ms.onnx \ --provider cpu \ --sample-rate 16000 \ --feature-dim 80 \ --num-threads 1 \ --decoding-method greedy_search \ --model-type zipformer2 \ --enable-endpoint-detection 0 \ --text-format none \ --enable-energy-tail-probe 1 \ --low-energy-rms 0.003 \ --speech-rms 0.010 \ --min-speech-ms 200 \ --min-silence-ms 500 \ --tail-probe-ms 500 \ --tail-probe-cooldown-ms 1000 ``` The default mode keeps `--enable-energy-tail-probe 0` and decodes only from client audio chunks. Tail-probe mode is useful for interactive voice-input demos where trailing partial results should refresh after the user pauses. Tune the RMS and silence thresholds according to microphone gain, background noise, and frontend chunking behavior. Test it with a WAV file: ```bash python infer_and_client/sherpa_streaming_client.py \ --server-uri ws://127.0.0.1:8766 \ --wav /path/to/test.wav \ --chunk-ms 100 \ --simulate-realtime 1 ``` For complete runtime options, see [deployment/README.md](deployment/README.md). For the script-level server/client guide and full parameter reference, see [deployment/infer_and_client/README.md](deployment/infer_and_client/README.md). ## ⚠️ Intended Use and Limitations - This release is intended for **Chinese-English ASR research, evaluation, demos, and deployment experiments**. - The current release focuses on **streaming and offline-streaming unified recognition**. - Production latency depends on hardware, concurrency, audio chunking, endpointing, and server configuration. - The technical report with training details, evaluation protocol, ablations, and additional analysis is **coming soon**. ## 📄 Citation The `X-ASR-zh-en` technical report is coming soon. Please cite the report once it is released. For now, refer to this model card and the GitHub project page. ## 📜 License This model is released under the **Apache-2.0 License**. ## 🙏 Acknowledgements This model is trained with **icefall** and deployed with **sherpa-onnx**. - icefall: https://github.com/k2-fsa/icefall - sherpa-onnx: https://github.com/k2-fsa/sherpa-onnx