Edit model card

Distil Whisper Small finetuned on PolyAI Minds14 English US.

This model is a fine-tuned version of distil-whisper/distil-small.en on the Speech Transcription in English from e-banking domain. dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0182
  • Wer Ortho: 0.3371
  • Wer: 0.3318

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 400
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.2325 3.57 100 0.6222 0.3557 0.3472
0.0196 7.14 200 0.8475 0.3757 0.3689
0.0014 10.71 300 0.9729 0.3630 0.3555
0.0006 14.29 400 1.0182 0.3371 0.3318

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.15.0
Downloads last month
5
Safetensors
Model size
166M params
Tensor type
F32
·
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 Shamik/distil-whisper-small-polyAI-minds14

Finetuned
(6)
this model

Dataset used to train Shamik/distil-whisper-small-polyAI-minds14

Space using Shamik/distil-whisper-small-polyAI-minds14 1

Evaluation results

  • Wer on Speech Transcription in English from e-banking domain.
    self-reported
    0.332