Edit model card

openai/whisper-large-v3

This model is a fine-tuned version of openai/whisper-large-v3 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5425
  • Wer: 41.0489

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1378 4.35 500 0.5576 51.2554
0.0024 8.7 1000 0.5425 41.0489

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.2.dev0
  • Tokenizers 0.15.0
Downloads last month
5
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 sanchit-gandhi/whisper-large-v3-ft-cv16-mn-freeze-encoder

Finetuned
(296)
this model

Evaluation results