metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: whisper-tiny-tamil
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: Speech Commands
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7142857142857143
whisper-tiny-tamil
This model is a fine-tuned version of openai/whisper-tiny on the Speech Commands dataset. It achieves the following results on the evaluation set:
- Loss: 0.6296
- Accuracy: 0.7143
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: 2
- eval_batch_size: 2
- 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9817 | 1.0 | 55 | 1.0006 | 0.5714 |
| 0.894 | 2.0 | 110 | 0.8903 | 0.5714 |
| 0.7656 | 3.0 | 165 | 0.8475 | 0.7143 |
| 0.5697 | 4.0 | 220 | 0.7843 | 0.6429 |
| 0.8338 | 5.0 | 275 | 0.7055 | 0.6429 |
| 0.6986 | 6.0 | 330 | 0.7369 | 0.7143 |
| 0.5099 | 7.0 | 385 | 0.6787 | 0.7143 |
| 0.5774 | 8.0 | 440 | 0.6369 | 0.7143 |
| 0.7313 | 9.0 | 495 | 0.6106 | 0.7857 |
| 0.5775 | 10.0 | 550 | 0.6296 | 0.7143 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.2.2
- Datasets 3.2.0
- Tokenizers 0.21.0