Whisper Turbo ig

This model is a fine-tuned version of deepdml/whisper-large-v3-turbo on the google/fleurs dataset. It achieves the following results on the evaluation set:

Loss: 0.7028
Wer: 31.2646
Cer: 10.8084

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.04
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.2019	0.2	1000	0.6438	36.4596	12.5223
0.1293	0.4	2000	0.6558	33.7633	11.6044
0.0589	0.6	3000	0.6882	31.8758	10.6653
0.0504	0.8	4000	0.6845	31.0669	10.3172
0.0353	1.0	5000	0.7028	31.2646	10.8084

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Citation

Please cite the model using the following BibTeX entry:

@misc{deepdml/whisper-large-v3-turbo-ig-mix-norm,
      title={Fine-tuned Whisper turbo ASR model for speech recognition in Lingala},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-large-v3-turbo-ig-mix-norm}},
      year={2025}
    }