metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
base_model: openai/whisper-tiny.en
model-index:
  - name: openai/whisper-tiny.en
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_pfs
          type: rishabhjain16/infer_pfs
          config: en
          split: test
        metrics:
          - type: wer
            value: 54.68
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_myst
          type: rishabhjain16/infer_myst
          config: en
          split: test
        metrics:
          - type: wer
            value: 17.56
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/infer_cmu
          type: rishabhjain16/infer_cmu
          config: en
          split: test
        metrics:
          - type: wer
            value: 33.53
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: rishabhjain16/libritts_dev_clean
          type: rishabhjain16/libritts_dev_clean
          config: en
          split: test
        metrics:
          - type: wer
            value: 14.71
            name: WER

openai/whisper-tiny.en

This model is a fine-tuned version of openai/whisper-tiny.en on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6129
Wer: 18.2504

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: 64
eval_batch_size: 32
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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3898	4.02	1000	0.4541	17.0533
0.2333	8.04	2000	0.4818	16.6839
0.0899	13.01	3000	0.5512	17.3679
0.0368	17.02	4000	0.5962	17.6199
0.0289	21.04	5000	0.6129	18.2504

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.9.1.dev0
Tokenizers 0.13.2