README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - librispeech
metrics:
  - wer
model-index:
  - name: Whisper Tiny English - Francesco Bonzi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: LibriSpeech ASR
          type: librispeech
          config: clean
          split: None
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 6.599969567863664

Whisper Tiny English - Francesco Bonzi

This model is a fine-tuned version of openai/whisper-tiny on the LibriSpeech ASR dataset. It achieves the following results on the evaluation set:

• Loss: 0.1858
• Wer: 6.6000

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: 16
• eval_batch_size: 8
• seed: 42
• 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
0.1884	0.56	1000	0.2044	7.2257
0.1119	1.12	2000	0.1911	6.8510
0.1203	1.68	3000	0.1873	6.6038
0.0832	2.24	4000	0.1858	6.6000

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0
• Datasets 2.18.0
• Tokenizers 0.15.2