README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - librispeech_asr
metrics:
  - wer
model-index:
  - name: whisper-small-libirClean-vs-commonNative-en
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: librispeech_asr
          type: librispeech_asr
          config: clean
          split: train
          args: clean
        metrics:
          - name: Wer
            type: wer
            value: 84.71153846153847

whisper-small-libirClean-vs-commonNative-en

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

• Loss: 2.3887
• Wer: 84.7115

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2459	0.26	10	3.6972	20.6731
0.83	0.53	20	2.9120	33.1731
0.5312	0.79	30	2.4692	76.6346
0.445	1.05	40	2.3355	65.8654
0.3173	1.32	50	2.3887	84.7115

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2