metadata
library_name: transformers
language:
- tw
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Small SerendepifyLabs Twi ASR
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: tw
split: None
args: 'config: tw, splits: [test,train+validation]'
metrics:
- type: wer
value: 85.13513513513513
name: Wer
Whisper Small SerendepifyLabs Twi ASR
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: 2.2557
- Wer: 85.1351
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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_steps: 100
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0004 | 20.0 | 100 | 2.1839 | 85.1351 |
| 0.0002 | 40.0 | 200 | 2.2297 | 85.1351 |
| 0.0002 | 60.0 | 300 | 2.2491 | 85.1351 |
| 0.0001 | 80.0 | 400 | 2.2557 | 85.1351 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2