metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- sinhala_asr
metrics:
- wer
model-index:
- name: whisper-tiny-si
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: sinhala_asr
type: sinhala_asr
config: default
split: test
args: default
metrics:
- name: Wer
type: wer
value: 169.24044840997482
whisper-tiny-si
This model is a fine-tuned version of openai/whisper-tiny on the sinhala_asr dataset. It achieves the following results on the evaluation set:
- Loss: 0.2660
- Wer: 169.2404
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: 16
- eval_batch_size: 16
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3098 | 1.6 | 1000 | 0.3362 | 183.1274 |
| 0.184 | 3.2 | 2000 | 0.2752 | 147.9181 |
| 0.1626 | 4.8 | 3000 | 0.2663 | 116.8383 |
| 0.1283 | 6.4 | 4000 | 0.2660 | 169.2404 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0