Hugging Face's logo

PradyumSomebody
/
whisper-small-hi-custom4

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
whisper-small-hi-custom4 / README.md
PradyumSomebody's picture
PradyumSomebody
End of training
0d3dde4 verified
preview code
|
raw
history blame contribute delete
3.05 kB
metadata
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - PradyumSomebody/Audio_Medical4
metrics:
  - wer
model-index:
  - name: Whisper Small EN - Pradyum Agarwal 4
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Audio Medical Combined Dataset
          type: PradyumSomebody/Audio_Medical4
          args: 'config: combined, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 0

Whisper Small EN - Pradyum Agarwal 4

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

  • Loss: 0.0009
  • Wer: 0.0

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: 10
  • 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: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.749 0.5556 25 0.8143 17.9088
0.6168 1.1111 50 0.6651 14.0483
0.4324 1.6667 75 0.3085 12.4397
0.1351 2.2222 100 0.1857 8.6863
0.1415 2.7778 125 0.1252 5.3083
0.0638 3.3333 150 0.0826 2.6810
0.053 3.8889 175 0.0494 1.7694
0.0303 4.4444 200 0.0282 0.9115
0.0252 5.0 225 0.0155 0.5362
0.012 5.5556 250 0.0111 0.4826
0.0119 6.1111 275 0.0051 0.1072
0.0029 6.6667 300 0.0035 0.0
0.0043 7.2222 325 0.0030 0.0536
0.0051 7.7778 350 0.0032 0.0536
0.0015 8.3333 375 0.0020 0.0
0.0013 8.8889 400 0.0016 0.0
0.001 9.4444 425 0.0015 0.0
0.0015 10.0 450 0.0011 0.0
0.0008 10.5556 475 0.0010 0.0
0.0007 11.1111 500 0.0009 0.0

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1