Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use aghannam/whisper-medium-ar-original with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aghannam/whisper-medium-ar-original with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="aghannam/whisper-medium-ar-original")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("aghannam/whisper-medium-ar-original") model = AutoModelForSpeechSeq2Seq.from_pretrained("aghannam/whisper-medium-ar-original", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 1cd504510c5cfeebdeb7b94bcc63c148d62a3bf3cddf299e2b8a730b22639d2e
- Size of remote file:
- 3.06 GB
- SHA256:
- 2816448cd152f76a8e1b52b46b04b42677f297c206d244af1cd5b62abb8e6e68
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.