Hugging Face's logo

adrianSauer
/
whisper-base-cer

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Guaraní
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-base-cer / README.md
adrianSauer's picture
adrianSauer
End of training
b010612 verified
preview code
|
raw
history blame contribute delete
1.77 kB
metadata
language:
  - gn
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
model-index:
  - name: Common Voice 16 - Guarani
    results: []

Common Voice 16 - Guarani

This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5864
  • Cer: 13.2164

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
2.3906 1.0101 100 0.9600 20.7738
0.578 2.0202 200 0.6882 16.1996
0.3116 3.0303 300 0.5999 14.6718
0.1741 4.0404 400 0.5747 13.5690
0.0955 5.0505 500 0.5864 13.2164

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1