This model is a fine-tuned version of openai/whisper-large-v3 on the Genius-Quebec-Rap-Top-150 dataset. It achieves the following results on the evaluation set:

Loss: 0.6369
Wer: 36.2272

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Github: https://github.com/ras0k/whisper-rap-queb

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 1600

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0	0	0.8603	56.3136
0.5418	12.5	200	0.6867	39.9158
0.4054	25.0	400	0.6274	37.6759
0.3577	37.5	600	0.6287	36.8129
0.3385	50.0	800	0.6329	36.5252
0.3178	62.5	1000	0.6364	36.8643
0.3191	75.0	1200	0.6371	36.3814
0.3210	87.5	1400	0.6369	36.2273
0.3197	100.0	1600	0.6370	36.5869

Framework versions

Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.6.1
Tokenizers 0.22.2

ras0k/whisper-rap-queb-v3

Whisper Quebec Rap - ras0k