Automatic Speech Recognition
Transformers
Safetensors
Min Nan Chinese
Chinese
whisper
taiwanese-hokkien
taigi
low-resource-language
fine-tuned
Instructions to use MediaTek-Research/Breeze-ASR-26 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MediaTek-Research/Breeze-ASR-26 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MediaTek-Research/Breeze-ASR-26")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("MediaTek-Research/Breeze-ASR-26") model = AutoModelForSpeechSeq2Seq.from_pretrained("MediaTek-Research/Breeze-ASR-26") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -140,4 +140,4 @@ This model is released under the [Apache 2.0 License](LICENSE).
|
|
| 140 |
|
| 141 |
## Acknowledgments
|
| 142 |
|
| 143 |
-
After more than two years of dedicated effort, we (
|
|
|
|
| 140 |
|
| 141 |
## Acknowledgments
|
| 142 |
|
| 143 |
+
After more than two years of dedicated effort, we ([**Speech AI Research Center@NYCU**](https://sites.google.com/nycu.edu.tw/sarc) and [**MediaTek Research**](https://www.mediatek.com/mediatekresearch)) have achieved initial **Taigi-to-Chinese ASR** results approaching commercial-grade performance, while **Taigi-to-Taibun ASR** versions are also under development. We sincerely thank the **Ministry of Economic Affairs** for its support in facilitating approval of the **NVIDIA Taipei-1** computing resource application, **Wistron** for sponsoring two DGX-H100 systems, and **Bronci** for providing various forms of support.
|