metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_19_0
metrics:
- wer
model-index:
- name: Drone Small En - Siang Yi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 19.0
type: mozilla-foundation/common_voice_19_0
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 29.365079365079367
Drone Small En - Siang Yi
This model is a fine-tuned version of openai/whisper-small on the Common Voice 19.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5365
- Wer: 29.3651
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 500.0 | 500 | 1.3457 | 26.9841 |
| 0.0 | 1000.0 | 1000 | 1.3710 | 26.9841 |
| 0.0 | 1500.0 | 1500 | 1.3774 | 26.9841 |
| 0.0 | 2000.0 | 2000 | 1.3967 | 28.5714 |
| 0.0 | 2500.0 | 2500 | 1.4267 | 28.5714 |
| 0.0 | 3000.0 | 3000 | 1.4544 | 28.5714 |
| 0.0 | 3500.0 | 3500 | 1.4849 | 29.3651 |
| 0.0 | 4000.0 | 4000 | 1.5152 | 29.3651 |
| 0.0 | 4500.0 | 4500 | 1.5297 | 29.3651 |
| 0.0 | 5000.0 | 5000 | 1.5365 | 29.3651 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0