Whisper Large V3 pl Fleurs Aug 2 - Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1295
  • Wer: 402.6139

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: 750
  • training_steps: 6000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0563 1.2579 1000 0.1102 448.8748
0.0144 2.5157 2000 0.1207 354.0117
0.0035 3.7736 3000 0.1205 514.6701
0.0009 5.0314 4000 0.1263 391.4104
0.0003 6.2893 5000 0.1280 385.1901
0.0001 7.5472 6000 0.1295 402.6139

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
16
Safetensors
Model size
1.54B 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 liqi03/whisper-large-v3-pl-aug2

Finetuned
(338)
this model

Dataset used to train liqi03/whisper-large-v3-pl-aug2

Evaluation results