metadata
language:
- ig
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Small Igbo - Obi Egwu
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: ig
split: test
args: ig
metrics:
- name: Wer
type: wer
value: 277.77777777777777
Whisper Small Igbo - Obi Egwu
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 5.0358
- Wer: 277.7778
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: 64
- 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 |
|---|---|---|---|---|
| 0.0 | 999.0002 | 1000 | 3.6182 | 91.6667 |
| 0.0 | 1999.0002 | 2000 | 4.2670 | 91.6667 |
| 0.0 | 2999.0002 | 3000 | 4.6511 | 91.6667 |
| 0.0 | 3999.0002 | 4000 | 5.0281 | 277.7778 |
| 0.0 | 4999.0002 | 5000 | 5.0358 | 277.7778 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1