Instructions to use reazon-research/japanese-hubert-base-k2-rs35kh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reazon-research/japanese-hubert-base-k2-rs35kh with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="reazon-research/japanese-hubert-base-k2-rs35kh")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("reazon-research/japanese-hubert-base-k2-rs35kh") model = AutoModelForCTC.from_pretrained("reazon-research/japanese-hubert-base-k2-rs35kh", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- b7f3fc933dfb4a96126886b9419b4899f15745cfec9f95d29bcd9ef4cbad11a9
- Size of remote file:
- 394 MB
- SHA256:
- 221e373f22a7007ca911d88774382fdf44c82eb609ba12c210086238df176a46
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.