--- license: other license_name: funasr-model-license-v1.1 license_link: https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE base_model: FunAudioLLM/SenseVoiceSmall pipeline_tag: automatic-speech-recognition library_name: openasr tags: - automatic-speech-recognition - speech-to-text - openasr - oasr - sensevoice ---
# SenseVoice Small Β· OpenASR **Fast multilingual speech recognition from FunAudioLLM β€” non-autoregressive SenseVoice, tuned for Chinese, Cantonese, English, Japanese and Korean** [![License](https://img.shields.io/badge/license-FunASR_Model_License_v1.1-2563eb.svg)](https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE) [![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr) [![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org) [![Base model](https://img.shields.io/badge/base-SenseVoiceSmall-f59e0b.svg)](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) Native speech-to-text in the **[OpenASR](https://github.com/QuintinShaw/openasr)** runtime β€” engineered for peak performance on CPU & GPU, **no Python at inference time**.
--- ## ✨ Highlights - 🌏 **Multilingual, zh-first** β€” high-precision Mandarin, Cantonese, English, Japanese and Korean with automatic language detection - ⚑ **Non-autoregressive speed** β€” an end-to-end architecture the upstream clocks at about 70 ms for 10 seconds of audio, 15 times faster than Whisper-Large - πŸ€„ **Chinese benchmark strength** β€” trained on over 400,000 hours of speech; the upstream reports better Chinese and Cantonese accuracy than Whisper on AISHELL and WenetSpeech - πŸͺΆ **Compact and local** β€” a small checkpoint that transcribes fully offline, from a 130 MB q4_k build up to full-fidelity fp16 - πŸ¦€ **Native in OpenASR** β€” `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU ## πŸš€ Quickstart ```bash # 1. Install the OpenASR CLI Β· https://openasr.org # 2. Pull a build (pick a quant β€” see the table below) openasr pull sensevoice-small:fp16 # 3. Transcribe openasr transcribe audio.wav --model sensevoice-small ``` All builds for this model: ```bash openasr pull sensevoice-small:fp16 openasr pull sensevoice-small:q8 openasr pull sensevoice-small:q4 ``` ## πŸ“¦ Available builds | Quant | File (`.oasr`) | Size | RAM peak | RTF Β· M1 CPU | RTF Β· M1 GPU | JFK Ξ”WER vs fp16 | |:------|:---------------|-----:|---------:|-------------:|-------------:|-----------------:| | fp16 | `sensevoice-small-fp16.oasr` | 470 MB | 745 MB | 0.18Γ— | 0.04Γ— | 0.0% | | q8_0 | `sensevoice-small-q8_0.oasr` | 252 MB | 514 MB | 0.18Γ— | 0.04Γ— | 0.0% | | q4_k | `sensevoice-small-q4_k.oasr` | 136 MB | 395 MB | 0.23Γ— | 0.05Γ— | 0.0% | RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK Ξ”WER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **fp16** is the recommended default β€” near-reference quality at a fraction of the footprint. ## 🧠 About SenseVoice Small SenseVoice Small is the compact member of **SenseVoice**, the speech understanding model family open-sourced by **FunAudioLLM** (Alibaba). Trained on more than **400,000 hours** of speech, it delivers high-precision transcription with automatic language detection for **Mandarin Chinese, Cantonese, English, Japanese and Korean**, and the upstream card reports Chinese and Cantonese accuracy ahead of Whisper on open benchmarks such as AISHELL and WenetSpeech. Its **non-autoregressive end-to-end** architecture makes inference exceptionally fast β€” the upstream team clocks about 70 ms for 10 seconds of audio, 15x faster than Whisper-Large. The upstream model also carries speech emotion recognition and audio event detection; the OpenASR packs currently surface plain transcription only (emotion/event tags are not yet exposed). This OpenASR repo repackages the original weights as `.oasr` packs that run natively in the OpenASR runtime β€” no Python at inference time. The **fp16** build is the recommended default for maximum fidelity; **q8_0** halves the footprint at near-reference quality and **q4_k** suits tight-memory devices. ## βš™οΈ How these packs were made Converted from [FunAudioLLM/SenseVoiceSmall](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) with the OpenASR importer: ```bash openasr model-pack import sensevoice .oasr \ --package-id sensevoice-small --quantization {fp16,q8-0,q4-k} ``` The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph buffer reuse to keep peak memory low. ## βš–οΈ License These packs **inherit the upstream model's license: FunASR Model License v1.1** ([source](https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE)). OpenASR packaging retains the upstream copyright and NOTICE; the only modifications are format conversion and quantization. ## πŸ™ Acknowledgements This pack is a redistribution of **SenseVoice Small**, created and open-sourced by the **FunAudioLLM team at Alibaba** ([FunAudioLLM/SenseVoiceSmall](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)), built on the **FunASR** open-source speech toolkit from Alibaba's ModelScope community. All credit for the original architecture, training, and weights belongs to the FunAudioLLM and FunASR teams; the license is inherited from and identical to the upstream model β€” the **[FunASR Model License v1.1](https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE)**, which permits commercial use and requires this attribution. Thank you to FunAudioLLM, the FunASR team, and Alibaba for releasing their work openly. OpenASR only performs format conversion, quantization, runtime verification, and local-inference adaptation. ## πŸ”— Links - πŸ¦€ **OpenASR** β€” - 🌐 **Website** β€” - πŸ€— **Upstream model** β€” [FunAudioLLM/SenseVoiceSmall](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)