Finetuned Whisper large-v2 for darija speech translation

This model is a fine-tuned version of openai/whisper-large-v2 on the Darija-C dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000
  • Bleu: 0.7440

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: 1
  • eval_batch_size: 1
  • 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: 100
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu
2.8484 0.8333 50 1.3002 0.0478
1.3282 1.6667 100 0.6981 0.2207
0.8624 2.5 150 0.3707 0.3989
0.5125 3.3333 200 0.1671 0.5491
0.2217 4.1667 250 0.1338 0.5698
0.2398 5.0 300 0.0775 0.6498
0.048 5.8333 350 0.0474 0.7083
0.0894 6.6667 400 0.0116 0.7344
0.0133 7.5 450 0.0009 0.7440
0.0009 8.3333 500 0.0023 0.7286
0.0029 9.1667 550 0.0002 0.7440
0.0004 10.0 600 0.0001 0.7440
0.0001 10.8333 650 0.0001 0.7440
0.0001 11.6667 700 0.0001 0.7440
0.0 12.5 750 0.0000 0.7440
0.0001 13.3333 800 0.0000 0.7440
0.0 14.1667 850 0.0000 0.7440
0.0 15.0 900 0.0000 0.7440
0.0 15.8333 950 0.0000 0.7440
0.0 16.6667 1000 0.0000 0.7440

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.21.0
Downloads last month
6
Safetensors
Model size
1.54B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Marialab/finetuned-whisper-large-v2-1000-step

Finetuned
(191)
this model