jinkrsmodel

This model is a fine-tuned version of openai/whisper-base on the DianaJin/voice dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2017
  • Cer: 134.5133

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: 5
  • training_steps: 40
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
No log 3.33 10 2.1701 13.2743
No log 6.67 20 1.3824 55.3097
1.7663 10.0 30 1.2305 164.1593
1.7663 13.33 40 1.2017 134.5133

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
22
Safetensors
Model size
764M 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 DianaJin/sample

Finetuned
(380)
this model