Breeze-ASR-25 ggml

ggml conversions of MediaTek-Research/Breeze-ASR-25 for whisper.cpp, made with whisper.cpp v1.9.4.

Original model: https://huggingface.co/MediaTek-Research/Breeze-ASR-25 β€” its card covers the model's languages, training and evaluation.

Files

File Type Size Description
ggml-breeze-asr-25.bin f16 3.1 GB Source precision
ggml-breeze-asr-25-q8_0.bin q8_0 1.7 GB 8-bit
ggml-breeze-asr-25-q5_0.bin q5_0 1.1 GB 5-bit, smallest

Download

hf download tsuzuri-app/Breeze-ASR-25-ggml ggml-breeze-asr-25-q5_0.bin --local-dir .

Usage

whisper-cli -m ggml-breeze-asr-25-q5_0.bin -l zh -f audio.wav

Tsuzuri, a subtitle editor, offers these files as the Breeze-ASR-25 preset under Settings β†’ Models β†’ Transcription.

Reproduce

Step Tool
Source breeze-asr-25.pt (fp16) at cffe7cc
Convert whisper.cpp v1.9.4 convert-pt-to-ggml.py
Tokenizer openai/whisper v20250625 assets
Quantize whisper.cpp v1.9.4 whisper-quantize

Every input is pinned by version and SHA256 in scripts/breeze.sh; run scripts/breeze.sh convert to rebuild the same files. The weights are unchanged apart from the format conversion and, for q8_0 and q5_0, quantization.

License

Apache-2.0, as the source model; see LICENSE.

Citation

@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}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for tsuzuri-app/Breeze-ASR-25-ggml

Quantized
(27)
this model

Paper for tsuzuri-app/Breeze-ASR-25-ggml