Instructions to use Or4kool/wolof_asr-lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Or4kool/wolof_asr-lm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Or4kool/wolof_asr-lm")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Or4kool/wolof_asr-lm") model = AutoModelForCTC.from_pretrained("Or4kool/wolof_asr-lm") - Notebooks
- Google Colab
- Kaggle
Or4kool/wolof_asr-lm
Or4kool/wolof_asr bundled with a KenLM n-gram decoder (language_model/) for beam-search decoding.
Decoder weights: alpha=0.9, beta=0.0.
Set MODEL_ID to this repo in the Wolof ASR service to enable beam search.
- Downloads last month
- 54
Model tree for Or4kool/wolof_asr-lm
Base model
Or4kool/wolof_asr