metadata

language:
  - nan
  - zh
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
model-index:
  - name: Whisper Small nan-tw - Taiwanese
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_16_1 nan-tw
          type: mozilla-foundation/common_voice_16_0
          config: nan-tw
          split: test
          args: nan-tw
        metrics:
          - name: CER
            type: cer
            value: 29.831606
metrics:
  - cer
pipeline_tag: automatic-speech-recognition

Whisper Small nan-tw - Taiwanese

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

Loss: 0.3880
Cer: 29.8316

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: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.6846	0.65	1000	0.6206	43.9508
0.3563	1.29	2000	0.4756	35.1554
0.29	1.94	3000	0.4050	31.3860
0.1704	2.58	4000	0.3880	29.8316

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2