whisper-v4

abedNa/whisper-v4

whisper-v4 is a machine learning model from abedNa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

6% of all-time downloads

All-time downloads

Public

Repo size

223 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors223 MB · 99%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Jan 26, 2026
Updated: Jan 26, 2026
SHA: 4a81eecd

Base models

ivrit-ai/whisper-large-v3-turbo

Model card

From the Hugging Face model README

whisper-v4

This model is a fine-tuned version of ivrit-ai/whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3019
Wer Ortho: 0.1547
Wer: 0.1048

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 800
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.3076	1.9608	100	0.3021	0.1497	0.0996
0.308	3.9216	200	0.3019	0.1547	0.1048

Framework versions

PEFT 0.18.1
Transformers 4.48.1
Pytorch 2.9.1+cu128
Datasets 3.6.0
Tokenizers 0.21.4

Library: peft
License: apache-2.0
Created: Jan 26, 2026
Updated: Jan 26, 2026