Whisper large LV - Felikss Kleins

This model is a fine-tuned version of AiLab-IMCS-UL/whisper-large-v3-lv-late-cv19 on the Recorded Voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1620
  • Wer: 10.8617

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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 250
  • training_steps: 2500

Training results

Training Loss Epoch Step Validation Loss Wer
0.0032 36.0360 1000 0.1513 12.6354
0.0007 72.0721 2000 0.1620 10.8617

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.4.1
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
37
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 FelixK7/whisper-large-lv-2

Finetuned
(2)
this model