metadata

language:
  - zh
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - thisiskeithkwan/canto
model-index:
  - name: whisper-small-canto-spaced
    results: []

whisper-small-canto-spaced

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

Loss: 0.6578
Cer: 2.1977

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

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.6643	0.38	500	0.6578	2.1977

Framework versions

Transformers 4.32.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.3
Tokenizers 0.13.3