Automatic Speech Recognition
Transformers
PyTorch
Moroccan Arabic
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use boumehdi/wav2vec2-large-xlsr-moroccan-darija with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use boumehdi/wav2vec2-large-xlsr-moroccan-darija with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="boumehdi/wav2vec2-large-xlsr-moroccan-darija")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("boumehdi/wav2vec2-large-xlsr-moroccan-darija") model = AutoModelForCTC.from_pretrained("boumehdi/wav2vec2-large-xlsr-moroccan-darija", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 8bb3b8ee24f7aaafb5af6e9438392438f22035781cadd7be3aaaa89d7c1d8d4e
- Size of remote file:
- 3.32 kB
- SHA256:
- c61dd66333a3a0d68eedaaf6d552d4521e71274edd381e8de2a88579575bba8c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.