Automatic Speech Recognition
Transformers
Safetensors
Korean
English
wav2vec2
ctc
korean
english
code-switching
Instructions to use raniczan/wav2vec2-xls-r-300m-korean-english with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use raniczan/wav2vec2-xls-r-300m-korean-english with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="raniczan/wav2vec2-xls-r-300m-korean-english")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("raniczan/wav2vec2-xls-r-300m-korean-english") model = AutoModelForCTC.from_pretrained("raniczan/wav2vec2-xls-r-300m-korean-english", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f91fa7f3dd898fb289af599df6132236533aac9327391315da39996b8d6be585
- Size of remote file:
- 1.26 GB
- SHA256:
- 95372f058bbd7e685f38f03f8d17f2ad5a5cda3cd0a945f218f73b63a4e28ae3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.