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: 85.53786155346116

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: 2.3358
• Wer: 85.5379

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
1.2481	0.08	10	3.5688	21.1895
0.7793	0.16	20	2.8307	38.9990
0.5443	0.24	30	2.4196	67.0458
0.4484	0.32	40	2.2903	71.1732
0.4086	0.4	50	2.3358	85.5379

Framework versions

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