metadata
language:
- or
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Odia v1.3
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0 or
type: mozilla-foundation/common_voice_11_0
config: or
split: test
args: or
metrics:
- name: Wer
type: wer
value: 29.055007052186177
Whisper Small Odia v1.3
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 or dataset. It achieves the following results on the evaluation set:
- Loss: 0.5570
- Wer: 29.0550
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- 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 |
|---|---|---|---|---|
| 0.0025 | 50.0 | 1000 | 0.4639 | 35.3456 |
| 0.0002 | 100.0 | 2000 | 0.5570 | 29.0550 |
| 0.0004 | 150.0 | 3000 | 0.6208 | 30.6347 |
| 0.0 | 200.0 | 4000 | 0.8745 | 33.5402 |
| 0.0 | 250.0 | 5000 | 0.9035 | 33.0042 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu102
- Datasets 2.10.0
- Tokenizers 0.13.2