muaalem-model-v2

obadx/muaalem-model-v2

muaalem-model-v2 is a machine learning model from obadx. 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 transformers. The card lists the license as mit.

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

Downloads · 30 days

58% of all-time downloads

All-time downloads

Public

Parameters

606M

2.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.4 GB · 100%

At a glance

Library: transformers
License: mit
Model type: multi_level_ctc
Access: Public
Created: Aug 13, 2025
Updated: Aug 14, 2025
SHA: 718c23dc

Base models

facebook/w2v-bert-2.0

Model card

From the Hugging Face model README

muaalem-model-v2

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0082
Per Phonemes: 0.0025
Per Hams Or Jahr: 0.0012
Per Shidda Or Rakhawa: 0.0017
Per Tafkheem Or Taqeeq: 0.0017
Per Itbaq: 0.0007
Per Safeer: 0.0011
Per Qalqla: 0.0007
Per Tikraar: 0.0008
Per Tafashie: 0.0015
Per Istitala: 0.0006
Per Ghonna: 0.0010
Average Per: 0.0012

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: 5e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
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: constant
lr_scheduler_warmup_ratio: 0.2
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Per Phonemes	Per Hams Or Jahr	Per Shidda Or Rakhawa	Per Tafkheem Or Taqeeq	Per Itbaq	Per Safeer	Per Qalqla	Per Tikraar	Per Tafashie	Per Istitala	Per Ghonna	Average Per
0.1584	0.2	712	0.0234	0.0063	0.0024	0.0031	0.0065	0.0017	0.0017	0.0018	0.0017	0.0035	0.0015	0.0020	0.0029
0.0168	0.4	1424	0.0149	0.0051	0.0020	0.0027	0.0031	0.0014	0.0016	0.0015	0.0013	0.0029	0.0013	0.0016	0.0022
0.0127	0.6	2136	0.0130	0.0045	0.0042	0.0027	0.0047	0.0014	0.0014	0.0016	0.0013	0.0022	0.0013	0.0019	0.0024
0.0123	0.8	2848	0.0100	0.0034	0.0017	0.0023	0.0025	0.0013	0.0013	0.0013	0.0012	0.0021	0.0014	0.0015	0.0018
0.0103	1.0	3560	0.0082	0.0025	0.0012	0.0017	0.0017	0.0007	0.0011	0.0007	0.0008	0.0015	0.0006	0.0010	0.0012

Framework versions

Transformers 4.55.0
Pytorch 2.8.0+cu128
Datasets 3.3.2
Tokenizers 0.21.4

Library: transformers
Type: multi_level_ctc
License: mit
Created: Aug 13, 2025
Updated: Aug 14, 2025