metadata

language:
  - vi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - vivos
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Sanchit Gandhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: '##'
          type: vivos
          config: vi
          split: None
          args: 'config: vi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 28.687356069744492

Whisper Small Hi - Sanchit Gandhi

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

Loss: 0.5230
Wer: 28.6874

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: 20
training_steps: 200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2772	0.57	100	0.5491	29.9594
0.1497	1.15	200	0.5230	28.6874

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2