GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AbdelrahmanHassan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AbdelrahmanHassan
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
This model has been fine-tuned using LoRA (Low-Rank Adaptation) to improve automatic speech recognition performance on Egyptian Arabic dialect.
python
import torchfrom transformers import WhisperProcessor, AutoModelForSpeechSeq2Seqfrom peft import PeftModelimport librosa # Load the model and processorprocessor = WhisperProcessor.from_pretrained("AbdelrahmanHassan/whisper-large-v3-egyptian-arabic")model = AutoModelForSpeechSeq2Seq.from_pretrained( "openai/whisper-large-v3", torch_dtype=torch.float16, low_cpu_mem_usage=True, use_safetensors=True) # Load the LoRA adaptermodel = PeftModel.from_pretrained(model, "AbdelrahmanHassan/whisper-large-v3-egyptian-arabic") # Load and process audioaudio, sr = librosa.load("path_to_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features # Generate transcriptionwith torch.no_grad(): predicted_ids = model.generate(input_features, max_length=225) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0] print(transcription)The model was trained on the Egyptian-ASR-MGB-3 dataset, which contains Egyptian Arabic speech samples.
If you use this model, please cite:
bibtex
@misc{whisper-egyptian-arabic, title={Whisper Large V3 Fine-tuned for Egyptian Arabic}, author={Your Name}, year={2025}, howpublished={\url{https://huggingface.co/AbdelrahmanHassan/whisper-large-v3-egyptian-arabic}}}This model is specifically fine-tuned for Egyptian Arabic dialect and may not perform well on other Arabic dialects or languages. The performance is dependent on the quality and diversity of the training data.
@misc{whisper-egyptian-arabic, title={Whisper Large V3 Fine-tuned for Egyptian Arabic}, author={Your Name}, year={2025}, howpublished={\url{https://huggingface.co/AbdelrahmanHassan/whisper-large-v3-egyptian-arabic}}}import torchfrom transformers import WhisperProcessor, AutoModelForSpeechSeq2Seqfrom peft import PeftModelimport librosa # Load the model and processorprocessor = WhisperProcessor.from_pretrained("AbdelrahmanHassan/whisper-large-v3-egyptian-arabic")model = AutoModelForSpeechSeq2Seq.from_pretrained( "openai/whisper-large-v3", torch_dtype=torch.float16, low_cpu_mem_usage=True, use_safetensors=True) # Load the LoRA adaptermodel = PeftModel.from_pretrained(model, "AbdelrahmanHassan/whisper-large-v3-egyptian-arabic") # Load and process audioaudio, sr = librosa.load("path_to_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features # Generate transcriptionwith torch.no_grad(): predicted_ids = model.generate(input_features, max_length=225) transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0] print(transcription)