README.md

metadata

language:
  - hre
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - ntviet/Hre-audio-dataset4
model-index:
  - name: >-
      Whisper Small Hre 4.4 - male and female voice - 1000 steps,  metric CER,
      skip_special_tokens False
    results: []

Whisper Small Hre 4.4 - male and female voice - 1000 steps, metric CER, skip_special_tokens False

This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 4 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0208
• Cer Ortho: 0.0214
• Cer: 1.0204

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer Ortho	Cer
0.013	4.13	1000	0.0208	0.0214	1.0204

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2