Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Arabic
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("gerryc/whisper-medium-ar")
model = AutoModelForSpeechSeq2Seq.from_pretrained("gerryc/whisper-medium-ar")Quick Links
Whisper Medium Ar - gerryc
Model was trained on CommonVoice Train. Tensorboard eval is on 256 samples of CommonVoice Dev.
Not normalized or lowercased. Evaluated and saved every 2500 steps. This model was overtrained and is overfitted. About 2000 to 4000 steps is around the best spot to stop training.
- Downloads last month
- 8
Evaluation results
- Wer on FLEURStest set self-reported52.800
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="gerryc/whisper-medium-ar")