Downloads · 30 days
201
51% of all-time downloads
phate334/Breeze-ASR-25-int8-CT2
Breeze-ASR-25-int8-CT2 is a automatic speech recognition model from phate334. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as apache-2.0.
這是 MediaTek-Research/Breeze-ASR-25 的 CTranslate2 int8 版本,可由 faster-whisper 載入。模型沒有額外微調。
Downloads · 30 days
201
51% of all-time downloads
All-time downloads
394
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin1.6 GB · 100%
From the Hugging Face model README
這是 MediaTek-Research/Breeze-ASR-25 的 CTranslate2 int8 版本,可由 faster-whisper 載入。模型沒有額外微調。
Breeze-ASR-25 基於 Whisper-large-v2,主要針對台灣華語、繁體中文語境、華英句內/句外混用與字幕時間對齊進行強化。
python -m pip install faster-whisper==1.2.1
from faster_whisper import WhisperModel
model = WhisperModel(
"YOUR_NAMESPACE/Breeze-ASR-25-int8-CT2",
device="cpu",
compute_type="int8",
)
segments, info = model.transcribe(
"audio.wav",
language="zh",
beam_size=5,
)
print(f"language={info.language} probability={info.language_probability:.3f}")
for segment in segments:
print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")
使用 CUDA 時可將 device 改成 cuda;支援 FP16 的 GPU 可搭配 compute_type="int8_float16"。
這是 CTranslate2 runtime artifact,不能用 transformers.AutoModel* 直接載入。
來源模型以 Apache License 2.0 釋出。使用前請一併閱讀來源模型卡。
@article{chou2025selfrefiningframeworkenhancingasr,
title={A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data},
author={Cheng Kang Chou and Chan-Jan Hsu and Ho-Lam Chung and Liang-Hsuan Tseng and Hsi-Chun Cheng and Yu-Kuan Fu and Kuan Po Huang and Hung-Yi Lee},
journal={arXiv preprint arXiv:2506.11130},
year={2025}
}