---
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper base AR - BA
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper base AR - BA

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1070
- Wer: 0.2297

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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_steps: 500
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Wer    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 78.8449       | 1.0     | 313   | 0.1892          | 0.7483 |
| 23.7046       | 2.0     | 626   | 0.1465          | 0.4188 |
| 13.1378       | 3.0     | 939   | 0.1347          | 0.3632 |
| 8.2072        | 4.0     | 1252  | 0.1312          | 0.3285 |
| 5.8166        | 5.0     | 1565  | 0.1316          | 0.2937 |
| 4.5461        | 6.0     | 1878  | 0.1339          | 0.2916 |
| 3.8785        | 7.0     | 2191  | 0.1276          | 0.2838 |
| 3.1975        | 8.0     | 2504  | 0.1253          | 0.2762 |
| 2.8784        | 9.0     | 2817  | 0.1240          | 0.2881 |
| 2.6303        | 10.0    | 3130  | 0.1238          | 0.2719 |
| 2.481         | 11.0    | 3443  | 0.1225          | 0.2670 |
| 2.2994        | 12.0    | 3756  | 0.1221          | 0.2641 |
| 2.0863        | 13.0    | 4069  | 0.1214          | 0.2672 |
| 2.0235        | 14.0    | 4382  | 0.1213          | 0.2638 |
| 2.015         | 14.9536 | 4680  | 0.1213          | 0.2626 |
| 7.0386        | 13.0    | 4875  | 0.1209          | 0.2760 |
| 5.2638        | 14.0    | 5250  | 0.1169          | 0.2538 |
| 3.8581        | 15.0    | 5625  | 0.1180          | 0.2374 |
| 3.4661        | 16.0    | 6000  | 0.1176          | 0.2408 |
| 2.8903        | 17.0    | 6375  | 0.1167          | 0.2359 |
| 2.6081        | 18.0    | 6750  | 0.1172          | 0.2358 |
| 2.6719        | 19.0    | 7125  | 0.1165          | 0.2401 |
| 2.4235        | 20.0    | 7500  | 0.1160          | 0.2430 |
| 4.9497        | 21.0    | 7875  | 0.1133          | 0.2361 |
| 3.6345        | 22.0    | 8250  | 0.1136          | 0.2274 |
| 3.092         | 23.0    | 8625  | 0.1123          | 0.2305 |
| 2.606         | 24.0    | 9000  | 0.1098          | 0.2283 |
| 2.4858        | 25.0    | 9375  | 0.1103          | 0.2253 |
| 2.1898        | 26.0    | 9750  | 0.1109          | 0.2327 |
| 2.1861        | 27.0    | 10125 | 0.1088          | 0.2311 |
| 1.8994        | 28.0    | 10500 | 0.1084          | 0.2261 |
| 1.8208        | 29.0    | 10875 | 0.1078          | 0.2266 |
| 1.706         | 30.0    | 11250 | 0.1077          | 0.2287 |
| 1.5895        | 31.0    | 11625 | 0.1067          | 0.2233 |
| 1.5086        | 32.0    | 12000 | 0.1068          | 0.2299 |
| 1.4744        | 33.0    | 12375 | 0.1065          | 0.2268 |
| 1.4184        | 34.0    | 12750 | 0.1056          | 0.2266 |
| 1.4134        | 35.0    | 13125 | 0.1064          | 0.2331 |
| 1.3246        | 36.0    | 13500 | 0.1054          | 0.2263 |
| 1.3368        | 37.0    | 13875 | 0.1057          | 0.2317 |
| 1.3084        | 38.0    | 14250 | 0.1053          | 0.2412 |
| 1.302         | 39.0    | 14625 | 0.1054          | 0.2309 |
| 1.2152        | 40.0    | 15000 | 0.1053          | 0.2297 |
| 3.6933        | 37.9994 | 15314 | 0.1044          | 0.2122 |
| 2.9938        | 39.0    | 15718 | 0.1051          | 0.2193 |
| 2.5582        | 40.0    | 16122 | 0.1041          | 0.2202 |
| 2.1949        | 41.0    | 16526 | 0.1032          | 0.2137 |
| 2.1428        | 42.0    | 16930 | 0.1045          | 0.2146 |
| 2.0052        | 43.0    | 17334 | 0.1027          | 0.2146 |
| 1.7204        | 44.0    | 17738 | 0.1031          | 0.2121 |
| 1.7391        | 45.0    | 18142 | 0.1026          | 0.2125 |
| 1.6544        | 46.0    | 18546 | 0.1028          | 0.2140 |
| 1.6764        | 47.0    | 18950 | 0.1033          | 0.2121 |
| 1.535         | 48.0    | 19354 | 0.1028          | 0.2122 |
| 1.5344        | 49.0    | 19758 | 0.1025          | 0.2163 |
| 1.5171        | 49.9721 | 20150 | 0.1025          | 0.2121 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1