miosipof's picture
End of training
f2c2df2 verified
metadata
base_model: openai/whisper-medium
datasets:
  - b-brave/speech_disorders_voice
language:
  - it
library_name: peft
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: Whisper Medium
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: b-brave/speech_disorders_voice
          type: b-brave/speech_disorders_voice
          config: default
          split: train
          args: default
        metrics:
          - type: wer
            value: 21.24248496993988
            name: Wer

Whisper Medium

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

  • Loss: 0.2798
  • Wer: 21.2425

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: 32
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • training_steps: 250
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.4644 1.0417 50 6.2039 73.7475
3.2455 2.0833 100 0.3363 23.6473
0.1546 3.125 150 0.2708 20.8417
0.0685 4.1667 200 0.2790 19.8397
0.0427 5.2083 250 0.2798 21.2425

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.4
  • Pytorch 2.2.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1