---
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: uaspeech-whisper-lg-3-Nov3
  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. -->

# uaspeech-whisper-lg-3-Nov3

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0571
- Wer: 8.1245

## 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: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 1.7741        | 0.0719 | 100  | 0.6537          | 58.1245 |
| 0.4975        | 0.1437 | 200  | 0.4079          | 39.8141 |
| 0.3739        | 0.2156 | 300  | 0.3398          | 33.3872 |
| 0.3037        | 0.2875 | 400  | 0.2941          | 30.2344 |
| 0.2783        | 0.3593 | 500  | 0.2456          | 26.1116 |
| 0.2568        | 0.4312 | 600  | 0.2270          | 25.1011 |
| 0.2012        | 0.5031 | 700  | 0.2372          | 25.9903 |
| 0.2139        | 0.5749 | 800  | 0.1828          | 21.3015 |
| 0.1649        | 0.6468 | 900  | 0.1750          | 19.7656 |
| 0.149         | 0.7186 | 1000 | 0.1640          | 19.4826 |
| 0.146         | 0.7905 | 1100 | 0.1444          | 17.5829 |
| 0.1424        | 0.8624 | 1200 | 0.1305          | 15.5214 |
| 0.116         | 0.9342 | 1300 | 0.1294          | 16.3703 |
| 0.121         | 1.0061 | 1400 | 0.1210          | 16.1277 |
| 0.0755        | 1.0783 | 1500 | 0.1022          | 13.7833 |
| 0.0754        | 1.1502 | 1600 | 0.0814          | 11.1156 |
| 0.0919        | 1.2221 | 1700 | 0.0849          | 11.6815 |
| 0.0801        | 1.2939 | 1800 | 0.0827          | 11.4794 |
| 0.0751        | 1.3658 | 1900 | 0.0757          | 10.3476 |
| 0.0727        | 1.4377 | 2000 | 0.0820          | 11.2773 |
| 0.0797        | 1.5095 | 2100 | 0.0582          | 8.5287  |
| 0.0712        | 1.5814 | 2200 | 0.0672          | 10.2264 |
| 0.0655        | 1.6533 | 2300 | 0.0736          | 10.2668 |
| 0.0635        | 1.7251 | 2400 | 0.0641          | 9.4988  |
| 0.0646        | 1.7970 | 2500 | 0.0552          | 8.8521  |
| 0.0618        | 1.8688 | 2600 | 0.0596          | 8.3670  |
| 0.063         | 1.9407 | 2700 | 0.0517          | 7.7607  |
| 0.0628        | 2.0126 | 2800 | 0.0448          | 6.2247  |
| 0.029         | 2.0844 | 2900 | 0.0571          | 8.1245  |


### Framework versions

- Transformers 4.43.4
- Pytorch 2.4.1
- Datasets 3.0.0
- Tokenizers 0.19.1