Views
No views yet
openai/whisper-large-v2 on approximately 10,000 hours of large-scale synthetic Taiwanese Hokkien speech data. The model transcribes spoken Taigi audio and outputs Mandarin Chinese character transcriptions.| Property | Value |
|---|---|
| Source model | MediaTek-Research/Breeze-ASR-26 |
| Architecture | Whisper Large V2 |
| Quantization | float16 |
| Model size | ~2.9 GB (vs ~6.2 GB float32 original) |
| CTranslate2 version | 4.7.1 |
1from faster_whisper import WhisperModel
2
3model = WhisperModel("MediaTek-Research/Breeze-ASR-26-ct2", device="cuda", compute_type="float16")
4# For CPU: WhisperModel("...", device="cpu", compute_type="int8")
5
6segments, info = model.transcribe("audio.wav", language="zh", task="transcribe")
7
8for segment in segments:
9 print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")Note: This model outputs Mandarin Chinese characters (not Taigi orthography / 台語正字). Passlanguage="zh"explicitly to avoid language detection overhead.
1@misc{lan2026breezetaigibenchmarksmodels,
2 title={Breeze Taigi: Benchmarks and Models for Taiwanese Hokkien Speech Recognition and Synthesis},
3 author={Yu-Siang Lan and Chia-Sheng Liu and Yi-Chang Chen and Po-Chun Hsu and Allyson Chiu and Shun-Wen Lin and Da-shan Shiu and Yuan-Fu Liao},
4 year={2026},
5 eprint={2603.19259},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2603.19259},
9}