metadata

library_name: transformers
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - kojo-george/asanti-twi-tts
metrics:
  - wer
model-index:
  - name: Whisper ASR Asanti Twi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: kojo-george/asanti-twi-tts
          type: asanti-twi-dataset
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 18.398768283294842

Whisper ASR Asanti Twi

This model is a fine-tuned version of openai/whisper-turbo on the kojo-george/asanti-twi-tts dataset. It achieves the following results on the evaluation set:

Loss: 0.2205
Wer: 18.3988

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: Use 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: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.226	0.5666	1000	0.3430	25.6197
0.1438	1.1331	2000	0.2737	20.8776
0.1277	1.6997	3000	0.2353	18.9530
0.083	2.2663	4000	0.2205	18.3988

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3