Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
hubert
speech-recognition
librispeech_asr
Generated from Trainer
Instructions to use patrickvonplaten/hubert-librispeech-clean-100h-demo-dist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use patrickvonplaten/hubert-librispeech-clean-100h-demo-dist with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="patrickvonplaten/hubert-librispeech-clean-100h-demo-dist")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("patrickvonplaten/hubert-librispeech-clean-100h-demo-dist") model = AutoModelForCTC.from_pretrained("patrickvonplaten/hubert-librispeech-clean-100h-demo-dist") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 04bbb8342cb0fb4c9a3de3f1917b3b6e0a0aa0bc3a5e5f9af2b697b502b5a240
- Size of remote file:
- 1.26 GB
- SHA256:
- 0ef5bfbb788429e991db277d00af496e70a875a03261753b97958d3ef8b22470
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.