GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
adelnazmy2002
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
adelnazmy2002
Model Tree
openai/whisper-small
Input Modalities
Output Modalities
Supported Functionality
Trained on MAdel121/arabic-egy-cleaned — a merged and cleaned corpus of Egyptian Arabic speech:
| Base model | openai/whisper-small |
| Hardware | Single NVIDIA RTX 4070 Super (16 GB VRAM) |
| Epochs | 3 per 10k-sample subset, 9 sequential subsets (~244k sample views) |
| Batch size | 32 / device + 2 gradient accumulation steps |
| Learning rate | 1e-5, 5% warmup |
| Precision | bf16/fp16 mixed precision, TF32 |
| Memory | Gradient checkpointing, checkpoints every 500 steps |
Because of limited local VRAM, the dataset was divided into 9 subsets of 10k samples and trained sequentially with resumable checkpoints.
Final validation loss: 0.488.
python
from transformers import WhisperProcessor, WhisperForConditionalGeneration, pipelineimport torchprocessor = WhisperProcessor.from_pretrained( "adelnazmy2002/egyptian-ammiya-whisper", language="arabic", task="transcribe",)model = WhisperForConditionalGeneration.from_pretrained( "adelnazmy2002/egyptian-ammiya-whisper" ) asr_pipe = pipeline( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, device=0 if torch.cuda.is_available() else -1, ) result = asr_pipe( "data/Recording_4.mp3", generate_kwargs={"language": "arabic", "task": "transcribe"},)print(result["text"])Or via faster-whisper / whisper pipelines — any standard Whisper inference path works, since this is a standard Whisper model checkpoint.
MIT
from transformers import WhisperProcessor, WhisperForConditionalGeneration, pipelineimport torchprocessor = WhisperProcessor.from_pretrained( "adelnazmy2002/egyptian-ammiya-whisper", language="arabic", task="transcribe",)model = WhisperForConditionalGeneration.from_pretrained( "adelnazmy2002/egyptian-ammiya-whisper" ) asr_pipe = pipeline( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, device=0 if torch.cuda.is_available() else -1, ) result = asr_pipe( "data/Recording_4.mp3", generate_kwargs={"language": "arabic", "task": "transcribe"},)print(result["text"])