metadata

language:
  - zh
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - whucedar/zh-CN
metrics:
  - wer
model-index:
  - name: zh-CN-model-medium - whucedar
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: zh-CN
          type: whucedar/zh-CN
          args: 'config: zh, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 517.7099236641221

zh-CN-model-medium - whucedar

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

Loss: 0.3110
Wer: 517.7099

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: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1157	0.6897	100	0.3224	301.8321
0.0737	1.3793	200	0.3057	395.5216
0.0153	2.0690	300	0.3026	531.1959
0.0154	2.7586	400	0.3081	387.7354
0.0051	3.4483	500	0.3110	517.7099

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu118
Datasets 2.20.0
Tokenizers 0.19.1