chinese-english-whisper-finetune

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

  • Loss: 0.6649
  • Wer: 59.1595
  • Mer: 50.2514

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: 0.0001
  • 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: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Mer
0.8854 0.2907 200 0.8722 59.5905 55.9986
0.6339 0.5814 400 0.6649 59.1595 50.2514

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
34
Safetensors
Model size
242M 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 shljessie/chinese-english-whisper-finetune

Finetuned
(2103)
this model