GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
montachouig
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
montachouig
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
ar)openai/whisper-large-v3out_proj, fc2, q_proj, v_proj, k_proj, fc1noneThe augmentation pipeline improves speech-recognition robustness by creating additional audio samples with synthetic room reverberation and white, pink, or brown background noise at randomized SNR levels. It preserves the original transcripts, segmentation, duration, and schema, while re-encoding augmented audio as WAV and retaining the original samples for fine-tuning.
The training data consists of audio and Tunisian Arabic transcript pairs. A reproducible 10% holdout split was created with seed 42. Dataset identity, license, size, and collection methodology were not recorded in the checkpoint; users should obtain those details from the model author before deployment.
| Hyperparameter | Value |
|---|---|
| Checkpoint step | 4,500 |
| Epochs configured | 10 |
| Learning rate | 0.0001 |
| Train batch size/device | 18 |
| Gradient accumulation | 4 |
| Effective batch size/device | 72 |
| Warmup steps | 500 |
| Weight decay | 0.0 |
| Precision | BF16 |
The best checkpoint reported by Trainer is outputs/whisper-large-v3-tunisian-arabic-lora/checkpoint-4500. The selected
validation metric is WER (lower is better); its recorded value is 21.743907.
WER/CER figures should not be interpreted without the held-out dataset details.
python
from peft import PeftModelfrom transformers import WhisperForConditionalGeneration base = WhisperForConditionalGeneration.from_pretrained( "openai/whisper-large-v3", torch_dtype="float32", device_map=None, # avoid bnb/accelerate quantized loading here) merged = PeftModel.from_pretrained(base, "montachouig/whisper-large-v3-tunisian").merge_and_unload()merged.save_pretrained("/path/to/merged-finetuned-whisper-v3") Install the runtime dependencies with
text
pip install transformers peft accelerate torch soundfileThis model is intended for research and transcription of Tunisian Arabic speech. Accuracy may degrade for other Arabic varieties, code-switching, noisy audio, unseen accents, specialized vocabulary, overlapping speakers, or long recordings. Whisper can hallucinate plausible text, so output should be reviewed by a human for medical, legal, safety-critical, or other high-impact uses. Do not use the model to infer sensitive traits or to transcribe people without an appropriate legal basis and consent.
The repository contains adapter and processor artifacts needed for inference.
The LINAGORA/LinTO Dataset Audio AR-TN was used to fine-tune the model.
| Generation beams | 4 |
| Maximum generated tokens | 225 |