Model reference · open weights
Breeze-ASR-25 is an open-weight audio or speech model from MediaTek-Research, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Breeze ASR 25 GitHub | Paper Breeze ASR 25 是一款基於 Whisper-large-v2 開發的語音辨識模型，並具有以下特色： - 強化繁體中文情境辨識能力 - 強化中英混用情境辨識能力，包含句內以及句外轉換 - 強化時間戳記對齊，適合自動字幕生成 Breeze ASR 25 is an advanced ASR model fine-tuned from Whisper-large-v2 - Optimized for Taiwanese Mandarin - Optimized for Mandarin-English code-switching scenarios, including intra-sentential switching and inter-sentential switching. - Enhanced time alignment, suitable for automatic captioning Example: 增強範例-中英混用情境： MediaTek's 24th Anniversary Breeze ASR 25: Whisper-large-v2: Performance Word error rates of benchmarks. The WERR is reported in comparison with the Whisper-large-v2 automatic language detection (WLV2-Auto) baseline. "Breeze ASR 25" is refered in the paper as "Twister" Short-form Audio Datasets Long-form Audio Datasets \ Code-switching datasets Training Data 所有 Breeze ASR 25 的的訓練取樣自寬鬆自由軟體授權條款的數據集，中文部分完全採用合成語音資料： The training data of Breeze ASR 25 is sampled from the following publicly available sources with permissive open-source licenses, where all Chinese data are synthetic: ODC Synth is generated by using text from FineWeb2 (ODC License) and a TTS model BreezyVoice (Apache2.0 License) Additional code-switching samples are generated through data augmentation with these three datasets; further details can be found in our paper. 🔧 Usage Example 字幕檔生成，請參考 GitHub Please refer to the GitHub for subtitles generation. For quick testing, the whisper architecture is supported in Hugging Face 🤗 Transformers. First, install relavant packages: The model can be used with the pipeline class to transcribe audios of arbitrary length: Simple change inputaudio.wav in the following example to the actual filename of your audio. You can obtain a wav file for testing by loading from a benchmark: Acknowledgements We thank NVIDIA for providing access to the Taipei-1 supercomputer. We thank Professor Hung-yi Lee for his valuable guidance on this project. 📜 Citation If you find this model useful, please cite our work: Cheng-Kang Chou\, Chan-Jan Hsu\, Ho-Lam Chung, Liang-Hsuan Tseng, Hsi-Chun Cheng, Yu-Kuan Fu, Kuan-Po Huang, Hung-yi Lee A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data \Equal contribution
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | MediaTek-Research |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 1.5B |
| Variants | 1 |
| Based on | openai/whisper-large-v2 |
| Released | 2025-06-06 |
| Popularity | 27k downloads / month |
| Likes | 142 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Breeze-ASR-25 | 1.5B | BF16 | ~3.5 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys breeze-asr-25 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (breeze-asr-25 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="breeze-asr-25" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗