metadata
language:
- my
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- chuuhtetnaing/myanmar-speech-dataset-openslr-80
model-index:
- name: 'Whisper-large-v3-myanmar '
results: []
Whisper-large-v3-myanmar
This model is a fine-tuned version of openai/whisper-large-v3 on the myanmar-speech-dataset-openslr-80 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1193
- Cer: 15.5255
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0542 | 3.5088 | 1000 | 0.0986 | 17.1755 |
| 0.0018 | 7.0175 | 2000 | 0.1193 | 15.5255 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1