whisper-fine-banking-dataset

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

  • Loss: 0.6014
  • Wer: 96.7495

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0001 32.26 1000 0.5225 96.6399
0.0 64.52 2000 0.5617 96.7495
0.0 96.77 3000 0.5931 96.7495
0.0 129.03 4000 0.6014 96.7495

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
29
Safetensors
Model size
764M params
Tensor type
F32
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for SharatChandra/whisper-fine-banking-dataset

Finetuned
(497)
this model

Space using SharatChandra/whisper-fine-banking-dataset 1