metadata
library_name: transformers
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Hausa
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: yo
split: test
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 75.6144027433797
Whisper Small Hausa
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5137
- Wer: 75.6144
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: 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0145 | 13.1579 | 1000 | 1.2374 | 76.6336 |
| 0.0017 | 26.3158 | 2000 | 1.4047 | 75.7668 |
| 0.0002 | 39.4737 | 3000 | 1.4648 | 75.6335 |
| 0.0001 | 52.6316 | 4000 | 1.4998 | 75.5763 |
| 0.0001 | 65.7895 | 5000 | 1.5137 | 75.6144 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1