README.md

metadata

language:
  - zh
license: apache-2.0
tags:
  - generated_from_trainer
base_model: openai/whisper-small
datasets:
  - mozilla-foundation/common_voice_16_1
model-index:
  - name: Wisper-Small-zh
    results: []

Wisper-Small-zh

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: 2.9956
• Cer: 105.1745

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: 400
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
3.033	0.5298	400	2.9956	105.1745

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1