Edit model card
Configuration Parsing Warning: In adapter_config.json: "peft.task_type" must be a string

Demo Model Whisper Large

This model is a fine-tuned version of EdoAbati/whisper-medium-it on the b-brave/speech_disorders_voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2483

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: 0.001
  • train_batch_size: 8
  • eval_batch_size: 4
  • 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: 64
  • num_epochs: 8
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.7042 0.75 48 0.4060
0.4224 1.5 96 0.3377
0.3628 2.25 144 0.3201
0.3135 3.0 192 0.2964
0.1907 3.75 240 0.2879
0.1446 4.5 288 0.3303
0.1011 5.25 336 0.2793
0.0678 6.0 384 0.2597
0.0421 6.75 432 0.2541
0.024 7.5 480 0.2483

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
4
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for miosipof/asr_michael_test_2.2

Adapter
this model

Dataset used to train miosipof/asr_michael_test_2.2