Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Incremental Swahili Luganda

This model is a fine-tuned version of openai/whisper-small on the Mix data dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3430
  • Wer: 31.7183

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • 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
0.2355 0.0894 500 0.3831 35.9432
0.2275 0.1789 1000 0.3818 35.3379
0.245 0.2683 1500 0.3727 34.4346
0.2321 0.3577 2000 0.3637 33.5439
0.2396 0.4472 2500 0.3569 32.9164
0.2231 0.5366 3000 0.3512 33.0780
0.2039 0.6261 3500 0.3468 32.3184
0.2283 0.7155 4000 0.3430 31.7183

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.2+cu118
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train mn720/inctraining3

Evaluation results