Automatic Speech Recognition
Transformers
Safetensors
Tigrinya
wav2vec2
african-languages
waxal
waxalnet
Instructions to use waxal-benchmarking/mms-300m-waxal-tir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use waxal-benchmarking/mms-300m-waxal-tir with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="waxal-benchmarking/mms-300m-waxal-tir")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("waxal-benchmarking/mms-300m-waxal-tir") model = AutoModelForCTC.from_pretrained("waxal-benchmarking/mms-300m-waxal-tir", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 8c1c46fb89cb8bd1792dee9706971e0d29695ae0b1f0cedc75c698bcf27baeea
- Size of remote file:
- 1.26 GB
- SHA256:
- 5100b347995f47b630647dadb7be24325776a13043fd3d1f47c0503a658ea561
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.