Instructions to use voidful/hubert-tiny-v2-unit-beamnorm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use voidful/hubert-tiny-v2-unit-beamnorm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="voidful/hubert-tiny-v2-unit-beamnorm")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("voidful/hubert-tiny-v2-unit-beamnorm") model = AutoModelForCTC.from_pretrained("voidful/hubert-tiny-v2-unit-beamnorm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- edcf83a710164209382170635d5d85ede064650dfdf363a6a321563b8aaece3c
- Size of remote file:
- 51.5 MB
- SHA256:
- 45cb0b5275db681e668164ee8049d691fd4a76986e844b21eadb5b448d149813
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.