Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Hebrew
wav2vec2
Generated from Trainer
robust-speech-event
Instructions to use imvladikon/wav2vec2-xls-r-300m-lm-hebrew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use imvladikon/wav2vec2-xls-r-300m-lm-hebrew with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="imvladikon/wav2vec2-xls-r-300m-lm-hebrew")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("imvladikon/wav2vec2-xls-r-300m-lm-hebrew") model = AutoModelForCTC.from_pretrained("imvladikon/wav2vec2-xls-r-300m-lm-hebrew", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c5fff6293c2cc32c208a04bda7eaa1d368029a69608506a16ba7d5f2b9ab34d2
- Size of remote file:
- 1.26 GB
- SHA256:
- 5f4ee7fbf1fd8b43c413809f06de6b07930c451e471decd5d7219a2704dee64c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.