whisper-uyghur-medium3

21f3002101/whisper-uyghur-medium3

whisper-uyghur-medium3 is a machine learning model from 21f3002101. 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

14% of all-time downloads

All-time downloads

Public

Repo size

75.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors9.5 MB · 63%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Jul 28, 2025
Updated: Jul 28, 2025
SHA: 8005480a

Base models

openai/whisper-medium

Model card

From the Hugging Face model README

whisper-uyghur-medium3

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

Cer: 0.1824
Loss: 0.8845

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: 0.0001
train_batch_size: 16
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Cer	Validation Loss
2.7137	0.6667	150	0.3007	1.8328
2.037	1.3333	300	0.2714	1.0958
1.8441	2.0	450	0.2380	1.0061
1.7696	2.6667	600	0.2201	0.9485
1.702	3.3333	750	0.2048	0.9171
1.7269	4.0	900	0.1818	0.8955
1.6546	4.6667	1050	0.1824	0.8845

Framework versions

PEFT 0.15.2
Transformers 4.54.0
Pytorch 2.7.1+cu126
Datasets 3.5.1
Tokenizers 0.21.2

Library: peft
License: apache-2.0
Created: Jul 28, 2025
Updated: Jul 28, 2025