Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use jcrkn/wav2vec2-large-xls-r-300m-bretonwelsh-colab with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jcrkn/wav2vec2-large-xls-r-300m-bretonwelsh-colab with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jcrkn/wav2vec2-large-xls-r-300m-bretonwelsh-colab")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("jcrkn/wav2vec2-large-xls-r-300m-bretonwelsh-colab") model = AutoModelForCTC.from_pretrained("jcrkn/wav2vec2-large-xls-r-300m-bretonwelsh-colab", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 35957a9fa5c96c38bc02ecfadaebb8033d9cc81325fefd1c2564f503c45ca020
- Size of remote file:
- 1.26 GB
- SHA256:
- 2d04acc1b12547579a197140716d21f48fef56a39dfe24c22587d32778a41b74
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.