metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-tiny-hi-capstone
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_16_1
        metrics:
          - type: wer
            value: 116.5644
            name: Wer
datasets:
  - mozilla-foundation/common_voice_16_1
language:
  - en
  - zh
  - de
  - es
  - ru
  - ko
  - fr
  - ja
  - pt
  - tr
  - pl
  - ca
  - nl
  - ar
  - sv
  - it
  - id
  - hi
  - fi
  - vi
  - he
  - uk
  - za
pipeline_tag: automatic-speech-recognition

whisper-tiny-hi-capstone

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2348
Wer: 116.5644

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: 14
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 56
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 25
training_steps: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.5312	0.02	25	1.3975	141.1837
1.3224	0.05	50	1.2348	116.5644

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.0
Tokenizers 0.15.0