Hugging Face's logo

Dev372
/
HarshDev-whisper-base-English_3000

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community

English Whisper Model

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

  • Loss: 0.1241
  • Wer: 8.2186

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: 3000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0573 3.0030 1000 0.1333 8.6703
0.0073 6.0060 2000 0.1185 8.2914
0.0009 9.0090 3000 0.1241 8.2186

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
1
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Dev372/HarshDev-whisper-base-English_3000

Base model

openai/whisper-base.en
Finetuned
(60)
this model

Dataset used to train Dev372/HarshDev-whisper-base-English_3000

Evaluation results